LING073 - User contributions [en]

User:Cpillsb1/Final project

2017-05-10T21:44:25Z

Cpillsb1:

My goal for the final project was to create a useful application for Apertium. Jonathan showed me the existing [http://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/pairviewer/apertium.html Apertium PairViewer], which is an interactive tool that visualizes the existing language pairs in Apertium. One idea that was in the works but no one had gotten around to was to create a 3D globe to visualize the language pairs. I was interested in learning JavaScript and HTML/CSS, so I decided to tackle this task as my final project for the class.
[[File:3D_Pairviewer.png|400px|thumb|right|3D Pairviewer]]
=Process=
Going into this project, I had no prior knowledge of any web development or JavaScript, but had some programming experience (Python, C++). A good chunk of time was spent simply reading up on how JS, HTML, and CSS interact, and more broadly, how the internet works.

The most common way of creating globes seemed to be by using D3.js and GeoJSON. I was able to find lots of incredibly helpful examples of people using these libraries (the examples I used are in the references). Most of the code is based on examples of somewhat similar problems.

To test the code locally I used Python's SimpleHTTPServer. I began by using code for a simple globe, and then tried to stitch pieces from other examples together. My workflow consisted of a lot of poking around, print statement debugging, and of course, StackOverflow. I did run into several hurdles along the way. One of the first difficulties was getting point data into the GeoJSON format so that it could be drawn. I initially inputted the Ling073 Pairs into this format by hand. Because I only had coordinates for a subset of the Apertium languages, I wrote a Python script that scraped the regular pair data and creates a GeoJSON file with the pairs that have coordinates. In the end I was able to implement all of the core functionality that I was aiming for.

=Features=
*'''Interactive''': My main goal was to create a fully rotatable globe, that conveys the language pair data in some form. The finished globe can be rotated by using mouse clicks.
*'''3D Arcs''': The program uses 3D arcs to indicate the language pairs. The arcs fade based on distance.
*'''Points''': The language locations are marked on the globe with points.
*'''Labels''': Each point is labelled with its language tag. These labels moved based on their position, and disappear when not visible on the globe.
*'''Tooltips''': The points and labels can be hovered to show a tooltip. The tooltip contains the language's three-letter tag and full name.
*'''Zooming''': There is a Zoom In and Zoom Out button that will zoom the globe by a Fixed Amount.
*'''Arc Coloring''': The arcs are color-coded by the repo status of the pair. The current color-coding is shown in the following table:
{|class="wikitable"
|-
! Status !! Description
|-
!style="background-color: lightgreen;"| '''trunk'''
| Released Language Pair
|-
!style="background-color: green;"| '''staging'''
| Extensively developed, but not yet released
|-
!style="background-color: yellow;"| '''nursery'''
| Can be built, but not extensively developed yet
|-
!style="background-color: red;"| '''incubator'''
| Dictionaries, fragments, rules
|-
!style="background-color: purple;"| '''Ling073-Spring'''
| Language pairs that were worked on this semester!
|}

= Bugs / Known Issues =
*Zooming in or out resets the globe to the default position, not where it was previously
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes
*Far away arcs fade a lot, making them difficult to be seen (e.g. Guarani to Warlpiri)

=Future Improvements=
*Implement mousewheel zooming (rather than using buttons)
*Arrowheads for arcs to indicate directionality?
*Separate coordinates from pair data in the JSON file.
*Include entire set of Apertium pairs, not just the trimmed down version
*Add a way to filter arcs or points
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Zoom buttons could be made prettier, possibly add scroll to zoom.

=Code=
The code is currently located at my personal Github linked [https://github.swarthmore.edu/cpillsb1/Ling073-Final here]. The repo contains all of the files that I used along the way. The Readme file contains more specific details about individual files and how to run it.

=References=
As mentioned earlier, I had a lot of help from various examples of using D3.js to create globes. The example codes were all either open-source or unlicensed. The following were the most useful examples that I used:
* http://bl.ocks.org/dwtkns/4973620
* https://bl.ocks.org/mbostock/6619561
* http://bl.ocks.org/KoGor/5994804
* http://bl.ocks.org/d3noob/a22c42db65eb00d4e369
* http://bl.ocks.org/dwtkns/4686432
* http://bl.ocks.org/d3noob/7030f35b72de721622b8
* http://bl.ocks.org/danielzurawski/3414137

[[Category: sp17_FinalProjects ]]

User:Cpillsb1/Final project

2017-05-10T21:43:54Z

Cpillsb1: /* Code */

My goal for the final project was to create a useful application for Apertium. Jonathan showed me the existing [http://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/pairviewer/apertium.html Apertium PairViewer], which is an interactive tool that visualizes the existing language pairs in Apertium. One idea that was in the works but no one had gotten around to was to create a 3D globe to visualize the language pairs. I was interested in learning JavaScript and HTML/CSS, so I decided to tackle this task as my final project for the class.
[[File:3D_Pairviewer.png|400px|thumb|right|Guarani IPA Keyboard]]
=Process=
Going into this project, I had no prior knowledge of any web development or JavaScript, but had some programming experience (Python, C++). A good chunk of time was spent simply reading up on how JS, HTML, and CSS interact, and more broadly, how the internet works.

The most common way of creating globes seemed to be by using D3.js and GeoJSON. I was able to find lots of incredibly helpful examples of people using these libraries (the examples I used are in the references). Most of the code is based on examples of somewhat similar problems.

To test the code locally I used Python's SimpleHTTPServer. I began by using code for a simple globe, and then tried to stitch pieces from other examples together. My workflow consisted of a lot of poking around, print statement debugging, and of course, StackOverflow. I did run into several hurdles along the way. One of the first difficulties was getting point data into the GeoJSON format so that it could be drawn. I initially inputted the Ling073 Pairs into this format by hand. Because I only had coordinates for a subset of the Apertium languages, I wrote a Python script that scraped the regular pair data and creates a GeoJSON file with the pairs that have coordinates. In the end I was able to implement all of the core functionality that I was aiming for.

=Features=
*'''Interactive''': My main goal was to create a fully rotatable globe, that conveys the language pair data in some form. The finished globe can be rotated by using mouse clicks.
*'''3D Arcs''': The program uses 3D arcs to indicate the language pairs. The arcs fade based on distance.
*'''Points''': The language locations are marked on the globe with points.
*'''Labels''': Each point is labelled with its language tag. These labels moved based on their position, and disappear when not visible on the globe.
*'''Tooltips''': The points and labels can be hovered to show a tooltip. The tooltip contains the language's three-letter tag and full name.
*'''Zooming''': There is a Zoom In and Zoom Out button that will zoom the globe by a Fixed Amount.
*'''Arc Coloring''': The arcs are color-coded by the repo status of the pair. The current color-coding is shown in the following table:
{|class="wikitable"
|-
! Status !! Description
|-
!style="background-color: lightgreen;"| '''trunk'''
| Released Language Pair
|-
!style="background-color: green;"| '''staging'''
| Extensively developed, but not yet released
|-
!style="background-color: yellow;"| '''nursery'''
| Can be built, but not extensively developed yet
|-
!style="background-color: red;"| '''incubator'''
| Dictionaries, fragments, rules
|-
!style="background-color: purple;"| '''Ling073-Spring'''
| Language pairs that were worked on this semester!
|}

= Bugs / Known Issues =
*Zooming in or out resets the globe to the default position, not where it was previously
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes
*Far away arcs fade a lot, making them difficult to be seen (e.g. Guarani to Warlpiri)

=Future Improvements=
*Implement mousewheel zooming (rather than using buttons)
*Arrowheads for arcs to indicate directionality?
*Separate coordinates from pair data in the JSON file.
*Include entire set of Apertium pairs, not just the trimmed down version
*Add a way to filter arcs or points
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Zoom buttons could be made prettier, possibly add scroll to zoom.

=Code=
The code is currently located at my personal Github linked [https://github.swarthmore.edu/cpillsb1/Ling073-Final here]. The repo contains all of the files that I used along the way. The Readme file contains more specific details about individual files and how to run it.

=References=
As mentioned earlier, I had a lot of help from various examples of using D3.js to create globes. The example codes were all either open-source or unlicensed. The following were the most useful examples that I used:
* http://bl.ocks.org/dwtkns/4973620
* https://bl.ocks.org/mbostock/6619561
* http://bl.ocks.org/KoGor/5994804
* http://bl.ocks.org/d3noob/a22c42db65eb00d4e369
* http://bl.ocks.org/dwtkns/4686432
* http://bl.ocks.org/d3noob/7030f35b72de721622b8
* http://bl.ocks.org/danielzurawski/3414137

[[Category: sp17_FinalProjects ]]

User:Cpillsb1/Final project

2017-05-10T21:43:31Z

Cpillsb1: /* Bugs / Known Issues */

My goal for the final project was to create a useful application for Apertium. Jonathan showed me the existing [http://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/pairviewer/apertium.html Apertium PairViewer], which is an interactive tool that visualizes the existing language pairs in Apertium. One idea that was in the works but no one had gotten around to was to create a 3D globe to visualize the language pairs. I was interested in learning JavaScript and HTML/CSS, so I decided to tackle this task as my final project for the class.
[[File:3D_Pairviewer.png|400px|thumb|right|Guarani IPA Keyboard]]
=Process=
Going into this project, I had no prior knowledge of any web development or JavaScript, but had some programming experience (Python, C++). A good chunk of time was spent simply reading up on how JS, HTML, and CSS interact, and more broadly, how the internet works.

The most common way of creating globes seemed to be by using D3.js and GeoJSON. I was able to find lots of incredibly helpful examples of people using these libraries (the examples I used are in the references). Most of the code is based on examples of somewhat similar problems.

To test the code locally I used Python's SimpleHTTPServer. I began by using code for a simple globe, and then tried to stitch pieces from other examples together. My workflow consisted of a lot of poking around, print statement debugging, and of course, StackOverflow. I did run into several hurdles along the way. One of the first difficulties was getting point data into the GeoJSON format so that it could be drawn. I initially inputted the Ling073 Pairs into this format by hand. Because I only had coordinates for a subset of the Apertium languages, I wrote a Python script that scraped the regular pair data and creates a GeoJSON file with the pairs that have coordinates. In the end I was able to implement all of the core functionality that I was aiming for.

=Features=
*'''Interactive''': My main goal was to create a fully rotatable globe, that conveys the language pair data in some form. The finished globe can be rotated by using mouse clicks.
*'''3D Arcs''': The program uses 3D arcs to indicate the language pairs. The arcs fade based on distance.
*'''Points''': The language locations are marked on the globe with points.
*'''Labels''': Each point is labelled with its language tag. These labels moved based on their position, and disappear when not visible on the globe.
*'''Tooltips''': The points and labels can be hovered to show a tooltip. The tooltip contains the language's three-letter tag and full name.
*'''Zooming''': There is a Zoom In and Zoom Out button that will zoom the globe by a Fixed Amount.
*'''Arc Coloring''': The arcs are color-coded by the repo status of the pair. The current color-coding is shown in the following table:
{|class="wikitable"
|-
! Status !! Description
|-
!style="background-color: lightgreen;"| '''trunk'''
| Released Language Pair
|-
!style="background-color: green;"| '''staging'''
| Extensively developed, but not yet released
|-
!style="background-color: yellow;"| '''nursery'''
| Can be built, but not extensively developed yet
|-
!style="background-color: red;"| '''incubator'''
| Dictionaries, fragments, rules
|-
!style="background-color: purple;"| '''Ling073-Spring'''
| Language pairs that were worked on this semester!
|}

= Bugs / Known Issues =
*Zooming in or out resets the globe to the default position, not where it was previously
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes
*Far away arcs fade a lot, making them difficult to be seen (e.g. Guarani to Warlpiri)

=Future Improvements=
*Implement mousewheel zooming (rather than using buttons)
*Arrowheads for arcs to indicate directionality?
*Separate coordinates from pair data in the JSON file.
*Include entire set of Apertium pairs, not just the trimmed down version
*Add a way to filter arcs or points
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Zoom buttons could be made prettier, possibly add scroll to zoom.

=Code=
The code is currently located at my personal Github linked [https://github.swarthmore.edu/cpillsb1/Ling073-Final here]. The repo contains all of the files that I used along the way. The Readme file contains more specific details.

=References=
As mentioned earlier, I had a lot of help from various examples of using D3.js to create globes. The example codes were all either open-source or unlicensed. The following were the most useful examples that I used:
* http://bl.ocks.org/dwtkns/4973620
* https://bl.ocks.org/mbostock/6619561
* http://bl.ocks.org/KoGor/5994804
* http://bl.ocks.org/d3noob/a22c42db65eb00d4e369
* http://bl.ocks.org/dwtkns/4686432
* http://bl.ocks.org/d3noob/7030f35b72de721622b8
* http://bl.ocks.org/danielzurawski/3414137

[[Category: sp17_FinalProjects ]]

User:Cpillsb1/Final project

2017-05-10T21:20:30Z

Cpillsb1:

My goal for the final project was to create a useful application for Apertium. Jonathan showed me the existing [http://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/pairviewer/apertium.html Apertium PairViewer], which is an interactive tool that visualizes the existing language pairs in Apertium. One idea that was in the works but no one had gotten around to was to create a 3D globe to visualize the language pairs. I was interested in learning JavaScript and HTML/CSS, so I decided to tackle this task as my final project for the class.
[[File:3D_Pairviewer.png|400px|thumb|right|Guarani IPA Keyboard]]
=Process=
Going into this project, I had no prior knowledge of any web development or JavaScript, but had some programming experience (Python, C++). A good chunk of time was spent simply reading up on how JS, HTML, and CSS interact, and more broadly, how the internet works.

The most common way of creating globes seemed to be by using D3.js and GeoJSON. I was able to find lots of incredibly helpful examples of people using these libraries (the examples I used are in the references). Most of the code is based on examples of somewhat similar problems.

To test the code locally I used Python's SimpleHTTPServer. I began by using code for a simple globe, and then tried to stitch pieces from other examples together. My workflow consisted of a lot of poking around, print statement debugging, and of course, StackOverflow. I did run into several hurdles along the way. One of the first difficulties was getting point data into the GeoJSON format so that it could be drawn. I initially inputted the Ling073 Pairs into this format by hand. Because I only had coordinates for a subset of the Apertium languages, I wrote a Python script that scraped the regular pair data and creates a GeoJSON file with the pairs that have coordinates. In the end I was able to implement all of the core functionality that I was aiming for.

=Features=
*'''Interactive''': My main goal was to create a fully rotatable globe, that conveys the language pair data in some form. The finished globe can be rotated by using mouse clicks.
*'''3D Arcs''': The program uses 3D arcs to indicate the language pairs. The arcs fade based on distance.
*'''Points''': The language locations are marked on the globe with points.
*'''Labels''': Each point is labelled with its language tag. These labels moved based on their position, and disappear when not visible on the globe.
*'''Tooltips''': The points and labels can be hovered to show a tooltip. The tooltip contains the language's three-letter tag and full name.
*'''Zooming''': There is a Zoom In and Zoom Out button that will zoom the globe by a Fixed Amount.
*'''Arc Coloring''': The arcs are color-coded by the repo status of the pair. The current color-coding is shown in the following table:
{|class="wikitable"
|-
! Status !! Description
|-
!style="background-color: lightgreen;"| '''trunk'''
| Released Language Pair
|-
!style="background-color: green;"| '''staging'''
| Extensively developed, but not yet released
|-
!style="background-color: yellow;"| '''nursery'''
| Can be built, but not extensively developed yet
|-
!style="background-color: red;"| '''incubator'''
| Dictionaries, fragments, rules
|-
!style="background-color: purple;"| '''Ling073-Spring'''
| Language pairs that were worked on this semester!
|}

= Bugs / Known Issues =
*Zooming in or out resets the globe to the default position, not where it was previously
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes

=Future Improvements=
*Implement mousewheel zooming (rather than using buttons)
*Arrowheads for arcs to indicate directionality?
*Separate coordinates from pair data in the JSON file.
*Include entire set of Apertium pairs, not just the trimmed down version
*Add a way to filter arcs or points
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Zoom buttons could be made prettier, possibly add scroll to zoom.

=Code=
The code is currently located at my personal Github linked [https://github.swarthmore.edu/cpillsb1/Ling073-Final here]. The repo contains all of the files that I used along the way. The Readme file contains more specific details.

=References=
As mentioned earlier, I had a lot of help from various examples of using D3.js to create globes. The example codes were all either open-source or unlicensed. The following were the most useful examples that I used:
* http://bl.ocks.org/dwtkns/4973620
* https://bl.ocks.org/mbostock/6619561
* http://bl.ocks.org/KoGor/5994804
* http://bl.ocks.org/d3noob/a22c42db65eb00d4e369
* http://bl.ocks.org/dwtkns/4686432
* http://bl.ocks.org/d3noob/7030f35b72de721622b8
* http://bl.ocks.org/danielzurawski/3414137

[[Category: sp17_FinalProjects ]]

File:3D Pairviewer.png

2017-05-10T21:17:52Z

Cpillsb1:

User:Cpillsb1/Final project

2017-05-10T21:16:10Z

Cpillsb1: /* References */

My goal for the final project was to create a useful application for Apertium. Jonathan showed me the existing [http://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/pairviewer/apertium.html Apertium PairViewer], which is an interactive tool that visualizes the existing language pairs in Apertium. One idea that was in the works but no one had gotten around to was to create a 3D globe to visualize the language pairs. I was interested in learning JavaScript and HTML/CSS, so I decided to tackle this task as my final project for the class.

=Process=
Going into this project, I had no prior knowledge of any web development or JavaScript, but had some programming experience (Python, C++). A good chunk of time was spent simply reading up on how JS, HTML, and CSS interact, and more broadly, how the internet works.

The most common way of creating globes seemed to be by using D3.js and GeoJSON. I was able to find lots of incredibly helpful examples of people using these libraries (the examples I used are in the references). Most of the code is based on examples of somewhat similar problems.

To test the code locally I used Python's SimpleHTTPServer. I began by using code for a simple globe, and then tried to stitch pieces from other examples together. My workflow consisted of a lot of poking around, print statement debugging, and of course, StackOverflow. I did run into several hurdles along the way. One of the first difficulties was getting point data into the GeoJSON format so that it could be drawn. I initially inputted the Ling073 Pairs into this format by hand. Because I only had coordinates for a subset of the Apertium languages, I wrote a Python script that scraped the regular pair data and creates a GeoJSON file with the pairs that have coordinates. In the end I was able to implement all of the core functionality that I was aiming for.

=Features=
*'''Interactive''': My main goal was to create a fully rotatable globe, that conveys the language pair data in some form. The finished globe can be rotated by using mouse clicks.
*'''3D Arcs''': The program uses 3D arcs to indicate the language pairs. The arcs fade based on distance.
*'''Points''': The language locations are marked on the globe with points.
*'''Labels''': Each point is labelled with its language tag. These labels moved based on their position, and disappear when not visible on the globe.
*'''Tooltips''': The points and labels can be hovered to show a tooltip. The tooltip contains the language's three-letter tag and full name.
*'''Zooming''': There is a Zoom In and Zoom Out button that will zoom the globe by a Fixed Amount.
*'''Arc Coloring''': The arcs are color-coded by the repo status of the pair. The current color-coding is shown in the following table:
{|class="wikitable"
|-
! Status !! Description
|-
!style="background-color: lightgreen;"| '''trunk'''
| Released Language Pair
|-
!style="background-color: green;"| '''staging'''
| Extensively developed, but not yet released
|-
!style="background-color: yellow;"| '''nursery'''
| Can be built, but not extensively developed yet
|-
!style="background-color: red;"| '''incubator'''
| Dictionaries, fragments, rules
|-
!style="background-color: purple;"| '''Ling073-Spring'''
| Language pairs that were worked on this semester!
|}

= Bugs / Known Issues =
*Zooming in or out resets the globe to the default position, not where it was previously
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes

=Future Improvements=
*Implement mousewheel zooming (rather than using buttons)
*Arrowheads for arcs to indicate directionality?
*Separate coordinates from pair data in the JSON file.
*Include entire set of Apertium pairs, not just the trimmed down version
*Add a way to filter arcs or points
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Zoom buttons could be made prettier, possibly add scroll to zoom.

=Code=
The code is currently located at my personal Github linked [https://github.swarthmore.edu/cpillsb1/Ling073-Final here]. The repo contains all of the files that I used along the way. The Readme file contains more specific details.

=References=
As mentioned earlier, I had a lot of help from various examples of using D3.js to create globes. The example codes were all either open-source or unlicensed. The following were the most useful examples that I used:
* http://bl.ocks.org/dwtkns/4973620
* https://bl.ocks.org/mbostock/6619561
* http://bl.ocks.org/KoGor/5994804
* http://bl.ocks.org/d3noob/a22c42db65eb00d4e369
* http://bl.ocks.org/dwtkns/4686432
* http://bl.ocks.org/d3noob/7030f35b72de721622b8
* http://bl.ocks.org/danielzurawski/3414137

[[Category: sp17_FinalProjects ]]

User:Cpillsb1/Final project

2017-05-10T21:15:31Z

Cpillsb1:

My goal for the final project was to create a useful application for Apertium. Jonathan showed me the existing [http://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/pairviewer/apertium.html Apertium PairViewer], which is an interactive tool that visualizes the existing language pairs in Apertium. One idea that was in the works but no one had gotten around to was to create a 3D globe to visualize the language pairs. I was interested in learning JavaScript and HTML/CSS, so I decided to tackle this task as my final project for the class.

=Process=
Going into this project, I had no prior knowledge of any web development or JavaScript, but had some programming experience (Python, C++). A good chunk of time was spent simply reading up on how JS, HTML, and CSS interact, and more broadly, how the internet works.

The most common way of creating globes seemed to be by using D3.js and GeoJSON. I was able to find lots of incredibly helpful examples of people using these libraries (the examples I used are in the references). Most of the code is based on examples of somewhat similar problems.

To test the code locally I used Python's SimpleHTTPServer. I began by using code for a simple globe, and then tried to stitch pieces from other examples together. My workflow consisted of a lot of poking around, print statement debugging, and of course, StackOverflow. I did run into several hurdles along the way. One of the first difficulties was getting point data into the GeoJSON format so that it could be drawn. I initially inputted the Ling073 Pairs into this format by hand. Because I only had coordinates for a subset of the Apertium languages, I wrote a Python script that scraped the regular pair data and creates a GeoJSON file with the pairs that have coordinates. In the end I was able to implement all of the core functionality that I was aiming for.

=Features=
*'''Interactive''': My main goal was to create a fully rotatable globe, that conveys the language pair data in some form. The finished globe can be rotated by using mouse clicks.
*'''3D Arcs''': The program uses 3D arcs to indicate the language pairs. The arcs fade based on distance.
*'''Points''': The language locations are marked on the globe with points.
*'''Labels''': Each point is labelled with its language tag. These labels moved based on their position, and disappear when not visible on the globe.
*'''Tooltips''': The points and labels can be hovered to show a tooltip. The tooltip contains the language's three-letter tag and full name.
*'''Zooming''': There is a Zoom In and Zoom Out button that will zoom the globe by a Fixed Amount.
*'''Arc Coloring''': The arcs are color-coded by the repo status of the pair. The current color-coding is shown in the following table:
{|class="wikitable"
|-
! Status !! Description
|-
!style="background-color: lightgreen;"| '''trunk'''
| Released Language Pair
|-
!style="background-color: green;"| '''staging'''
| Extensively developed, but not yet released
|-
!style="background-color: yellow;"| '''nursery'''
| Can be built, but not extensively developed yet
|-
!style="background-color: red;"| '''incubator'''
| Dictionaries, fragments, rules
|-
!style="background-color: purple;"| '''Ling073-Spring'''
| Language pairs that were worked on this semester!
|}

= Bugs / Known Issues =
*Zooming in or out resets the globe to the default position, not where it was previously
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes

=Future Improvements=
*Implement mousewheel zooming (rather than using buttons)
*Arrowheads for arcs to indicate directionality?
*Separate coordinates from pair data in the JSON file.
*Include entire set of Apertium pairs, not just the trimmed down version
*Add a way to filter arcs or points
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Zoom buttons could be made prettier, possibly add scroll to zoom.

=Code=
The code is currently located at my personal Github linked [https://github.swarthmore.edu/cpillsb1/Ling073-Final here]. The repo contains all of the files that I used along the way. The Readme file contains more specific details.

=References=
As mentioned earlier, I had a lot of help from various examples of using D3.js to create globes. The example codes were all either open-source or unlicensed. The following were the most useful examples that I used:
* [http://bl.ocks.org/dwtkns/4973620]
* [https://bl.ocks.org/mbostock/6619561]
* [http://bl.ocks.org/KoGor/5994804]
* [http://bl.ocks.org/d3noob/a22c42db65eb00d4e369]
* [http://bl.ocks.org/dwtkns/4686432]
* [http://bl.ocks.org/d3noob/7030f35b72de721622b8]
* [http://bl.ocks.org/danielzurawski/3414137]

[[Category: sp17_FinalProjects ]]

User:Cpillsb1/Final project

2017-05-10T21:09:46Z

Cpillsb1:

My goal for the final project was to create a useful application for Apertium. Jonathan showed me the existing [http://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/pairviewer/apertium.html Apertium PairViewer], which is an interactive tool that visualizes the existing language pairs in Apertium. One idea that was in the works but no one had gotten around to was to create a 3D globe to visualize the language pairs. I was interested in learning JavaScript and HTML/CSS, so I decided to tackle this task as my final project for the class.
= 3D Globe Language Pair Visualizer =

Specifics about the individual files used are given in the ReadMe in the Github repo (linked at bottom).

=Process=
Going into this project, I had no prior knowledge of any web development or JavaScript, but had some programming experience (Python, C++). A good chunk of time was spent simply reading up on how JS, HTML, and CSS interact, and more broadly, how the internet works.

The most common way of creating globes seemed to be by using D3.js and GeoJSON. I was able to find lots of incredibly helpful examples of people using these libraries (the examples I used are in the references). Most of the code is based on examples of somewhat similar problems.

To test the code locally I used Python's SimpleHTTPServer. I began by using code for a simple globe, and then tried to stitch pieces from other examples together. My workflow consisted of a lot of poking around, print statement debugging, and of course, StackOverflow. I did run into several hurdles along the way. One of the first difficulties was getting point data into the GeoJSON format so that it could be drawn. I initially inputted the Ling073 Pairs into this format by hand. Because I only had coordinates for a subset of the Apertium languages, I wrote a Python script that scraped the regular pair data and creates a GeoJSON file with the pairs that have coordinates. In the end I was able to implement all of the core functionality that I was aiming for.

=Features=
*'''Interactive''': My main goal was to create a fully rotatable globe, that conveys the language pair data in some form. The finished globe can be rotated by using mouse clicks.
*'''3D Arcs''': The program uses 3D arcs to indicate the language pairs. The arcs fade based on distance.
*'''Points''': The language locations are marked on the globe with points.
*'''Labels''': Each point is labelled with its language tag. These labels moved based on their position, and disappear when not visible on the globe.
*'''Tooltips''': The points and labels can be hovered to show a tooltip. The tooltip contains the language's three-letter tag and full name.
*'''Zooming''': There is a Zoom In and Zoom Out button that will zoom the globe by a Fixed Amount.
*'''Arc Coloring''': The arcs are color-coded by the repo status of the pair. The current color-coding is shown in the following table:
{|class="wikitable"
|-
! Status !! Description
|-
!style="background-color: lightgreen;"| '''trunk'''
| Released Language Pair
|-
!style="background-color: green;"| '''staging'''
| Extensively developed, but not yet released
|-
!style="background-color: yellow;"| '''nursery'''
| Can be built, but not extensively developed yet
|-
!style="background-color: red;"| '''incubator'''
| Dictionaries, fragments, rules
|-
!style="background-color: purple;"| '''Ling073-Spring'''
| Language pairs that were worked on this semester!
|}

= Bugs / Known Issues =
*Zooming in or out resets the globe to the default position, not where it was previously
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes

=Future Improvements=
*Implement mousewheel zooming (rather than using buttons)
*Arrowheads for arcs to indicate directionality?
*Separate coordinates from pair data in the JSON file.
*Include entire set of Apertium pairs, not just the trimmed down version
*Add a way to filter arcs or points
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Zoom buttons could be made prettier, possibly add scroll to zoom.

=Code=

=Citations=
[[Category: sp17_FinalProjects ]]

User:Cpillsb1/Final project

2017-05-10T21:09:13Z

Cpillsb1:

My goal for the final project was to create a useful application for Apertium. Jonathan showed me the existing [http://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/pairviewer/apertium.html Apertium PairViewer], which is an interactive tool that visualizes the existing language pairs in Apertium. One idea that was in the works but no one had gotten around to was to create a 3D globe to visualize the language pairs. I was interested in learning JavaScript and HTML/CSS, so I decided to tackle this task as my final project for the class.
= 3D Globe Language Pair Visualizer =

Specifics about the individual files used are given in the ReadMe in the Github repo (linked at bottom).

=Process=
Going into this project, I had no prior knowledge of any web development or JavaScript, but had some programming experience (Python, C++). A good chunk of time was spent simply reading up on how JS, HTML, and CSS interact, and more broadly, how the internet works.

The most common way of creating globes seemed to be by using D3.js and GeoJSON. I was able to find lots of incredibly helpful examples of people using these libraries (the examples I used are in the references). Most of the code is based on examples of somewhat similar problems.

To test the code locally I used Python's SimpleHTTPServer. I began by using code for a simple globe, and then tried to stitch pieces from other examples together. My workflow consisted of a lot of poking around, print statement debugging, and of course, StackOverflow. I did run into several hurdles along the way. One of the first difficulties was getting point data into the GeoJSON format so that it could be drawn. I initially inputted the Ling073 Pairs into this format by hand. Because I only had coordinates for a subset of the Apertium languages, I wrote a Python script that scraped the regular pair data and creates a GeoJSON file with the pairs that have coordinates.

In the end I was able to implement all of the core functionality that I was aiming for.

=Features=
*'''Interactive''': My main goal was to create a fully rotatable globe, that conveys the language pair data in some form. The finished globe can be rotated by using mouse clicks.
*'''3D Arcs''': The program uses 3D arcs to indicate the language pairs. The arcs fade based on distance.
*'''Points''': The language locations are marked on the globe with points.
*'''Labels''': Each point is labelled with its language tag. These labels moved based on their position, and disappear when not visible on the globe.
*'''Tooltips''': The points and labels can be hovered to show a tooltip. The tooltip contains the language's three-letter tag and full name.
*'''Zooming''': There is a Zoom In and Zoom Out button that will zoom the globe by a Fixed Amount.
*'''Arc Coloring''': The arcs are color-coded by the repo status of the pair. The current color-coding is shown in the following table:
{|class="wikitable"
|-
! Status !! Description
|-
!style="background-color: lightgreen;"| '''trunk'''
| Released Language Pair
|-
!style="background-color: green;"| '''staging'''
| Extensively developed, but not yet released
|-
!style="background-color: yellow;"| '''nursery'''
| Can be built, but not extensively developed yet
|-
!style="background-color: red;"| '''incubator'''
| Dictionaries, fragments, rules
|-
!style="background-color: purple;"| '''Ling073-Spring'''
| Language pairs that were worked on this semester!
|}

==3D Arcs==
The program uses 3D arcs to indicate the language pairs

= Bugs / Known Issues =
*Zooming in or out resets the globe to the default position, not where it was previously
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes

=Future Improvements=
*Implement mousewheel zooming (rather than using buttons)
*Arrowheads for arcs to indicate directionality?
*Separate coordinates from pair data in the JSON file.
*Include entire set of Apertium pairs, not just the trimmed down version
*Add a way to filter arcs or points
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Zoom buttons could be made prettier, possibly add scroll to zoom.

=Code=

=Citations=
[[Category: sp17_FinalProjects ]]

User:Cpillsb1/Final project

2017-05-10T20:34:04Z

Cpillsb1: /* Process */

User:Cpillsb1/Final project

2017-05-10T20:15:43Z

Cpillsb1:

User:Cpillsb1/Final project

2017-05-10T20:07:09Z

Cpillsb1: /* Bugs / Future improvements */

= 3D Globe Language Pair Visualizer =

= Bugs / Future improvements =
*Zooming in or out resets the globe to the default position, not where it was previously
*No indicator for directionality of pairs currently
*Ideally coordinate data should be separated from the pairs in the JSON file, and then can be looked up by looking at the point_data.
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Zoom buttons could be made prettier, possibly add scroll to zoom.
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future
*Currently ignores all two letter language codes. Should add conversions from two to three letter codes

[[Category: sp17_FinalProjects ]]

User:Cpillsb1/Final project

2017-05-10T19:59:01Z

Cpillsb1:

User:Cpillsb1/Final project

2017-05-10T19:48:10Z

Cpillsb1:

User:Cpillsb1/Final project

2017-05-10T19:44:02Z

Cpillsb1: /* Bugs / Future improvements */

== 3D Globe Pair visualizer ==

== Bugs / Future improvements ==
*Zooming in or out resets the globe to the default position, not where it was previously
*No indicator for directionality of pairs currently
*Ideally coordinate data should be separated from the pairs in the JSON file, and then can be looked up by looking at the point_data.
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Zoom buttons could be made prettier, possibly add scroll to zoom.
*Colors indicating repo of the pair are pretty ugly, tried to base it off the original pairviewer color scheme
*Tooltip doesn't fit long names. Perhaps make tooltip size scaleable in the future

User:Cpillsb1/Final project

2017-05-10T19:30:50Z

Cpillsb1: /* Bugs / Future improvements */

User:Cpillsb1/Final project

2017-05-09T22:12:27Z

Cpillsb1: /* Bugs / Future improvements */

== 3D Globe Pair visualizer ==

== Bugs / Future improvements ==
*Currently, arcs and labels will have weird behavior after zooming in or out
*Zooming in or out resets the globe to the default position, not where it was previously
*No indicator for directionality of pairs currently
*Ideally coordinate data should be separated from the pairs in the JSON file, and then can be looked up by looking at the point_data.
*Certain values are still hardcoded, should be changed to be dynamic in the future
*Zoom buttons could be made prettier, possibly add scroll to zoom.

User:Cpillsb1/Final project

2017-05-09T21:55:44Z

Cpillsb1: /* Bugs / Known issues */

User:Cpillsb1/Final project

2017-05-09T21:54:02Z

Cpillsb1: Created page with "== 3D Globe Pair visualizer == == Bugs / Known issues == *Currently, arcs and labels will have weird behavior after zooming in or out *Zooming in or out resets the globe to..."

== 3D Globe Pair visualizer ==

== Bugs / Known issues ==
*Currently, arcs and labels will have weird behavior after zooming in or out
*Zooming in or out resets the globe to the default position, not where it was previously
*No indicator for directionality of pairs currently
*Ideally coordinate data should be separated from the pairs in the JSON file, and then can be looked up by looking at the point_data.
*

Guarani

2017-04-26T03:03:55Z

Cpillsb1: /* Developed Resources */

=External Resources=
==Computational Resources==
*Spellchecker
**Found a paper in Spanish about a Guarani spell-checker being worked on [https://www.scribd.com/doc/186935076/Corrector-ortografico-para-Guarani here]. However, no option to download was found.

*'''Guarani: A case study in resource development for quick ramp-up MT''' [http://s3.amazonaws.com/academia.edu.documents/30506035/amta-2006-abdelali.pdf?AWSAccessKeyId=AKIAIWOWYYGZ2Y53UL3A&Expires=1485234655&Signature=hUbkxoir5ZC2VoGfEvgDmQHnwx8%3D&response-content-disposition=inline%3B%20filename%3DGuarani_a_case_study_in_resource_develop.pdf]
**Paper that talks about a method for developing quick ramp-up machine translation. Uses Guarani as an example. Written by team of researchers at New Mexico State University, unsure about license.

==Dictionaries==
*'''Guaraní Concise Dictionary: Guaraní-English, English-Guaraní''' by A. Scott Britton
**E-book of a English-Guarani dictionary. Licenses is all rights reserved. [https://books.google.com.py/books?id=l3V5j5I2oXkC&printsec=frontcover&hl=es-419#v=onepage&q&f=false]
*'''Glosbe Online Dictionary'''
**Website containing Guarani dictionaries for several languages [https://glosbe.com/gn/ here]. Website says that some data is licensed.

==Grammatical Descriptions==
*Scanned PDF of a introductory Guarani course book (in English) made by the Peace Corps. Unsure of the license. [http://files.eric.ed.gov/fulltext/ED200014.pdf] [http://files.eric.ed.gov/fulltext/ED200015.pdf]

*'''Curso básico de Guaraní''' CERDET (Centro de Estudios Regionales para el Desarrollo de Tarija)
**PDF in Spanish that teaches the basics of Guarani grammar [http://www.cerdet.org.bo/images/stories/biblioteca/Curso.pdf here]. Couldn't find license.

*Spanish Wikibooks page with several links to pages on the grammar of Guarani (free license). [https://es.wikibooks.org/wiki/Guaran%C3%AD/Gram%C3%A1tica]

==Scientific Works==
*'''The Grammar of Possession: Inalienability, Incorporation and Possessor Ascension in Guarani''' - Maura Velázquez-Castillo
**Scholarly work on the grammar of Guarani. Focuses on alienable and inalienable possession. The e-book is available [http://site.ebrary.com/lib/swarthmore/reader.action?docID=10495931 online]. Copyrighted.

*'''On the Prosodic Coding of Focus in Paraguayan Guaraní'''[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.656.2890&rep=rep1&type=pdf] - Cynthia G. Clopper and Judith Tonhauser
**Scholarly paper focused mostly on the phonetics and phonology of Guarani, but does include a large section on the grammar of Guarani. Copyrighted, all rights reserved.

*'''The Distribution of Differential Object Marking in Paraguayan Guaraní'''[https://etd.ohiolink.edu/!etd.send_file?accession=osu1243450139] - Cory Adam Shain
**Thesis written on the object marking of direct objects in Guarani. Includes lots of example sentences and an extensive summary of the syntax of Guarani. All rights reserved.

*'''Word Order in Paraguayan Guaraní'''[http://www.journals.uchicago.edu/doi/pdfplus/10.1086/652267] - Judith Tonhauser and Erika Colijn
**Scholarly article about word order and grammar of Guarani. Includes lots of example sentences with English translation. All rights reserved.

==Corpora==

*Bible Passage Translations
**Online copy of a translation of the Bible.[https://www.bible.com/bible/66/jhn.1] Has been approved by the bishops of Paraguay. [https://www.catholicculture.org/news/headlines/index.cfm?storyid=27821]

*Wikipedia Pages
**There are 3,000 Wikipedia pages in Guarani, however, many of the pages are very sparse.[https://gn.wikipedia.org/w/index.php?title=Mba%27ech%C4%A9ch%C4%A9:Todas&from=Aguara+p%C3%B3pe&hideredirects=1] Pages for movies and TV shows seem to have a decent amount of text.[https://gn.wikipedia.org/wiki/The_Simpsons1]

*'''Let's Talk Guarnime''' [http://letstalkguaranime.blogspot.com/]
**Blog written in English by a Peace Corps volunteer in Paraguay. Teaches the grammar of Guarani and contains lots of example text in Guarani along with English translation. Unsure about license, will try to contact author.

=Developed Resources=
==UDpipe==
*Link to udpipe wikipage [https://wikis.swarthmore.edu/ling073/Guarani/Universal_Dependencies here]
*Link to corpus repository that contains udpipe [https://github.swarthmore.edu/cpillsb1/ling073-gug-corpus here]
==Guarani Keyboard==
*Link to wiki [https://wikis.swarthmore.edu/ling073/Guarani/Keyboard here].
*Link to github repository [https://github.swarthmore.edu/cpillsb1/ling-073-gug-keyboard here].
==Corpus==
*Link to github repository [https://github.swarthmore.edu/cpillsb1/ling073-gug-corpus here].

*Resources for machine translation between Guarani and Warlpiri [https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri]
[[Category:Guarani]] [[Category:sp17_ResourceDocumentation]]

Guarani/Universal Dependencies

2017-04-26T03:01:28Z

Cpillsb1:

=Evaluation=
==Corpora==
{| class="wikitable"
|+Information
|-
|
|Number of sentences
|Number of forms
|-
|<code>gug.annotated.ud.conllu</code>
| 33
| 158
|-
|<code>gug.annotated2.ud.conllu</code>
| 23
| 103
|}

==Withmorph==
Here are the results from using <code>gug.withmorph.udpipe</code> on the two conllu files:

{| class="wikitable"
|+Results
|-
|
|UAS
|LAS
|-
|<code>gug.annotated.ud.conllu</code>
| 91.14%
| 78.48%
|-
|<code>gug.annotated2.ud.conllu</code>
| 60.19%
| 47.57%
|}

==Nomorph==
Here are the results from using <code>gug.nomorph.udpipe</code> on the two conllu files:

{| class="wikitable"
|+Results
|-
|
|UAS
|LAS
|-
|<code>gug.annotated.ud.conllu</code>
| 60.13%
| 50.00%
|-
|<code>gug.annotated2.ud.conllu</code>
| 33.01%
| 26.21%
|}

=Dependency Relations=
==nsubj==
The nsubj relation is used to mark nominal subjects. In languages like English, we almost always have a word that acts as the nominal subject (occasionally there are implied subjects like in "Go!"). However, in Guarani, because person is marked on verbs as a prefix, there often sentences that do not have a distinct word that acts as a the nominal subject.

Consider the English sentence "I eat." In this sentence, we would mark "I" as the nsubj. However, in Guarani we could write the equivalent sentence as "Akaru" ("karu" = eat, "a-" = I), or as "Che akaru" ("che" = I). The first person pronoun is optional in this case. Because there is not a good way to mark a word as both a root and an nsubj, I ended up with some sentences that did not have an nsubj. Here are two example sentences:
* "Oguata." (He/She walks). In this sentence, "Oguata" is both the root and the nsubj.
* "Che aguata." (I walk). In this sentence, "che" is the nsubj and "aguata" is the root.

==nummod==
The nummod relation came up fairly frequently in my corpora. I think this is mostly due to the fact that the word "peteĩ" (One) is often used as an indefinite determiner. Consider the following sentences:
*"Peteĩ jagua opo" (A/One dog jumps). In this sentence, it seems plausible to tag "peteĩ" as either a nummod or det.
*"Mokoĩ ava ajeroky" (Two men dance). In this sentence, "mokoĩ" (two) is a nummod for "ava" (man).

==amod==
The amod relation also came up fairly frequently in my corpora. The amod usually just behaves like it would in English. Adjectives are generally amods. Consider the following phrases:
*"ahy'o rasy" (sore throat). In this sentence, "ahy'o" throat is modified by the adjective "rasy" (sore"). Here, "rasy" is an amod.
*"Jakare kuña" (female crocodile). In this sentence, "jakare" (crocodile) is modified by the noun "kuña" (woman). Here, "kuña" is an amod, even though the lemma is a noun.

==det==
Determiners were also frequent in the corpora. Guarani borrows the definite determiner "la" from Spanish. However, it is often optional. As mentioned early, the word "peteĩ" (one) often acts as an indefinite determiner. Consider the following sentences:
* "Maria okambia la istória" (Maria changes the story). Here, the word "la" (~the) acts as the definite determiner for "istória" (story).
* "Otopa peteĩ ita" (He/she throws a/one stone). Here, the word "peteĩ" (one) can be viewed as either an indefinite determiner for "ita' (stone), or as a nummod for "ita."

==obj==
Direct objects in Guarani are usually marked with the suff "-pe." Sometimes, the suffix is not included (I couldn't find an explanation for when it is or is necessary). Consider the following sentences:
* "Peteĩ jagua ohecha mbarakajape" (A dog looks at a cat). Here, the word "mbarakaja" (cat) is behaving as the direct object of the verb "ohecha" (he/she/it looks), so "mbarakaja" gets the suffix "-pe."
* "Nde reguereko y" (You have water). Here, the word "y" (water) is the direct object of the root "reguereko" (you have). However, note that "y" does not have the suffix "-pe" in this case.

[[Category:sp17_UD]]

Guarani/Universal Dependencies

2017-04-26T02:16:13Z

Cpillsb1:

=Evaluation=
Number of sentences:
*<code>gug.annotated.ud.conllu</code>:
*<code>gug.annotated2.ud.conllu</code>:

==Corpora==
{| class="wikitable"
|+Information
|-
|
|Number of sentences
|Number of forms
|-
|<code>gug.annotated.ud.conllu</code>
| 33
| 158
|-
|<code>gug.annotated2.ud.conllu</code>
| 23
| 103
|}

Here are the results from parsing gug.annotated.ud.txt and gug.annotated2.ud.txt:

[[Category:sp17_UD]]

Guarani/Universal Dependencies

2017-04-25T02:26:49Z

Cpillsb1: Created page with "Category:sp17_UD"

[[Category:sp17_UD]]

Guarani and Warlpiri

2017-04-20T16:24:26Z

Cpillsb1: /* MT wbp->gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
====6 new lexical selection rules====
* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

====4 new twol rules====
*Nasal harmony on dative suffix -pe:
**-pe now properly changes to -me when before a nasal vowel.
**Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
echo "havõme" | apertium -d . gug-morph
^havõme/havõ<n><sg><dat>$^./.<sent>$

*Nasal harmony on accusative suffix -ve:
**-ve now properly changes to -me on accusative forms of pronouns
**Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
echo "peẽme" | apertium -d . gug-morph
^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$

*Stress on accusative forms of pronouns:
**The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
**Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
echo "chéve" | apertium -d . gug-morph
^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$

*Nasal harmony on reflexive prefix je- :
**je- now properly changes to -ñe when before a nasal.
**Ex: ñeñapytĩ (“to tie”).
echo "oñeñapytĩ" | apertium -d . gug-morph
^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><nowiki><ref></nowiki>$^./.<sent>$

===Tests results (GUG)===
*Precision and recall:
**Results:
precisionRecall ../corpus/ling073-gug-corpus/ling073-gug-corpus/gug.annotated.basic.txt ../bootstrap/ling073-gug/corpus.out.txt
Totals: 89 tp, 87 fp, 0 tn, 19 fn
Precision: 82.40741%
Recall: 50.56818%

*Coverage over large corpus:
**Results:
aq-covtest ~/Source/corpus/ling073-gug-corpus/ling073-gug-corpus/gug.corpus.large.txt gug.automorf.bin
Number of tokenised words in the corpus: 522284
Coverage: 28.96%

*Number of stems in transducer: ~270 (didn't count by hand)

===MT wbp->gug===
*WER and PER
Number of words in reference: 76
Number of words in test: 69
Number of unknown words (marked with a star) in test: 45
Percentage of unknown words: 65.22 %
Word error rate (WER): 100.00 %
Position-independent word error rate (PER): 94.74 %
*Proportion of stems translate correctly in longer: 31/71 = 40.8%

Unsure... Need wbp.longer.txt to test in longer and large

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T16:22:49Z

Cpillsb1: /* MT wbp->gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
====6 new lexical selection rules====
* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

====4 new twol rules====
*Nasal harmony on dative suffix -pe:
**-pe now properly changes to -me when before a nasal vowel.
**Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
echo "havõme" | apertium -d . gug-morph
^havõme/havõ<n><sg><dat>$^./.<sent>$

*Nasal harmony on accusative suffix -ve:
**-ve now properly changes to -me on accusative forms of pronouns
**Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
echo "peẽme" | apertium -d . gug-morph
^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$

*Stress on accusative forms of pronouns:
**The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
**Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
echo "chéve" | apertium -d . gug-morph
^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$

*Nasal harmony on reflexive prefix je- :
**je- now properly changes to -ñe when before a nasal.
**Ex: ñeñapytĩ (“to tie”).
echo "oñeñapytĩ" | apertium -d . gug-morph
^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><nowiki><ref></nowiki>$^./.<sent>$

===Tests results (GUG)===
*Precision and recall:
**Results:
precisionRecall ../corpus/ling073-gug-corpus/ling073-gug-corpus/gug.annotated.basic.txt ../bootstrap/ling073-gug/corpus.out.txt
Totals: 89 tp, 87 fp, 0 tn, 19 fn
Precision: 82.40741%
Recall: 50.56818%

*Coverage over large corpus:
**Results:
aq-covtest ~/Source/corpus/ling073-gug-corpus/ling073-gug-corpus/gug.corpus.large.txt gug.automorf.bin
Number of tokenised words in the corpus: 522284
Coverage: 28.96%

*Number of stems in transducer: ~270 (didn't count by hand)

===MT wbp->gug===
*WER and PER
Number of words in reference: 76
Number of words in test: 69
Number of unknown words (marked with a star) in test: 45
Percentage of unknown words: 65.22 %
Word error rate (WER): 100.00 %
Position-independent word error rate (PER): 94.74 %

Unsure... Need wbp.longer.txt to test in longer and large

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T16:22:38Z

Cpillsb1: /* MT wbp->gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
====6 new lexical selection rules====
* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

====4 new twol rules====
*Nasal harmony on dative suffix -pe:
**-pe now properly changes to -me when before a nasal vowel.
**Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
echo "havõme" | apertium -d . gug-morph
^havõme/havõ<n><sg><dat>$^./.<sent>$

*Nasal harmony on accusative suffix -ve:
**-ve now properly changes to -me on accusative forms of pronouns
**Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
echo "peẽme" | apertium -d . gug-morph
^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$

*Stress on accusative forms of pronouns:
**The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
**Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
echo "chéve" | apertium -d . gug-morph
^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$

*Nasal harmony on reflexive prefix je- :
**je- now properly changes to -ñe when before a nasal.
**Ex: ñeñapytĩ (“to tie”).
echo "oñeñapytĩ" | apertium -d . gug-morph
^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><nowiki><ref></nowiki>$^./.<sent>$

===Tests results (GUG)===
*Precision and recall:
**Results:
precisionRecall ../corpus/ling073-gug-corpus/ling073-gug-corpus/gug.annotated.basic.txt ../bootstrap/ling073-gug/corpus.out.txt
Totals: 89 tp, 87 fp, 0 tn, 19 fn
Precision: 82.40741%
Recall: 50.56818%

*Coverage over large corpus:
**Results:
aq-covtest ~/Source/corpus/ling073-gug-corpus/ling073-gug-corpus/gug.corpus.large.txt gug.automorf.bin
Number of tokenised words in the corpus: 522284
Coverage: 28.96%

*Number of stems in transducer: ~270 (didn't count by hand)

===MT wbp->gug===
*WER and PER
**
Number of words in reference: 76
Number of words in test: 69
Number of unknown words (marked with a star) in test: 45
Percentage of unknown words: 65.22 %
Word error rate (WER): 100.00 %
Position-independent word error rate (PER): 94.74 %

Unsure... Need wbp.longer.txt to test in longer and large

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T05:33:03Z

Cpillsb1: /* Final Evaluation */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
====6 new lexical selection rules====
* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

====4 new twol rules====
*Nasal harmony on dative suffix -pe:
**-pe now properly changes to -me when before a nasal vowel.
**Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
echo "havõme" | apertium -d . gug-morph
^havõme/havõ<n><sg><dat>$^./.<sent>$

*Nasal harmony on accusative suffix -ve:
**-ve now properly changes to -me on accusative forms of pronouns
**Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
echo "peẽme" | apertium -d . gug-morph
^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$

*Stress on accusative forms of pronouns:
**The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
**Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
echo "chéve" | apertium -d . gug-morph
^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$

*Nasal harmony on reflexive prefix je- :
**je- now properly changes to -ñe when before a nasal.
**Ex: ñeñapytĩ (“to tie”).
echo "oñeñapytĩ" | apertium -d . gug-morph
^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><nowiki><ref></nowiki>$^./.<sent>$

===Tests results (GUG)===
*Precision and recall:
**Results:
precisionRecall ../corpus/ling073-gug-corpus/ling073-gug-corpus/gug.annotated.basic.txt ../bootstrap/ling073-gug/corpus.out.txt
Totals: 89 tp, 87 fp, 0 tn, 19 fn
Precision: 82.40741%
Recall: 50.56818%

*Coverage over large corpus:
**Results:
aq-covtest ~/Source/corpus/ling073-gug-corpus/ling073-gug-corpus/gug.corpus.large.txt gug.automorf.bin
Number of tokenised words in the corpus: 522284
Coverage: 28.96%

*Number of stems in transducer: ~270 (didn't count by hand)

===MT wbp->gug===
*WER and PER
**Unsure... Need wbp.longer.txt to test in longer and large

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T04:25:13Z

Cpillsb1: /* 4 new twol rules */

Guarani and Warlpiri

2017-04-20T04:24:00Z

Cpillsb1: /* 4 new twol rules */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
====6 new lexical selection rules====
* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

====4 new twol rules====
*Nasal harmony on dative suffix -pe:
**-pe now properly changes to -me when before a nasal vowel.
**Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
echo "havõme" | apertium -d . gug-morph
^havõme/havõ<n><sg><dat>$^./.<sent>$

*Nasal harmony on accusative suffix -ve:
**-ve now properly changes to -me on accusative forms of pronouns
**Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
echo "peẽme" | apertium -d . gug-morph
^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$

*Stress on accusative forms of pronouns:
**The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
**Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
echo "chéve" | apertium -d . gug-morph
^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$

*Nasal harmony on reflexive prefix je- :
**je- now properly changes to -ñe when before a nasal.
**Ex: ñeñapytĩ (“to tie”).
echo "oñeñapytĩ" | apertium -d . gug-morph
^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><ref >$^./.<sent>$

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T04:22:01Z

Cpillsb1: /* 4 new twol rules */

Guarani and Warlpiri

2017-04-20T04:21:14Z

Cpillsb1: /* 4 new twol rules */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
====6 new lexical selection rules====
* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

====4 new twol rules====
*Nasal harmony on dative suffix -pe:
**-pe now properly changes to -me when before a nasal vowel.
**Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
echo "havõme" | apertium -d . gug-morph
^havõme/havõ<n><sg><dat>$^./.<sent>$

*Nasal harmony on accusative suffix -ve:
**-ve now properly changes to -me on accusative forms of pronouns
**Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
echo "peẽme" | apertium -d . gug-morph
^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$

*Stress on accusative forms of pronouns:
**The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
**Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
echo "chéve" | apertium -d . gug-morph
^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$

*Nasal harmony on reflexive prefix je- :
**je- now properly changes to -ñe when before a nasal.
**Ex: ñeñapytĩ (“to tie”).
echo "oñeñapytĩ" | apertium -d . gug-morph
^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><ref>$^./.<sent>$

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T04:20:34Z

Cpillsb1: /* wbp → gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
====6 new lexical selection rules====
* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

====4 new twol rules====
*Nasal harmony on dative suffix -pe:
**-pe now properly changes to -me when before a nasal vowel.
**Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
echo "havõme" | apertium -d . gug-morph
^havõme/havõ<n><sg><dat>$^./.<sent>$

*Nasal harmony on accusative suffix -ve:
**-ve now properly changes to -me on accusative forms of pronouns
**Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
echo "peẽme" | apertium -d . gug-morph
^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$

*Stress on accusative forms of pronouns:
**The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
**Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
echo "chéve" | apertium -d . gug-morph
^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$

*Nasal harmony on reflexive prefix je- :
**je- now properly changes to -ñe when before a nasal.
**Ex: ñeñapytĩ (“to tie”).
echo "oñeñapytĩ" | apertium -d . gug-morph
^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><ref>$^./.<sent>$

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T04:13:37Z

Cpillsb1: /* 6 new lexical selection rules */

Guarani and Warlpiri

2017-04-20T04:13:26Z

Cpillsb1: /* 6 new lexical selection rules */

Guarani and Warlpiri

2017-04-20T04:13:15Z

Cpillsb1: /* wbp → gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
====6 new lexical selection rules====
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
** Rule: select "mboy'u" if "muru-pinyi" is followed by food or drink words: "ngapa" (water/grog), "pama" (liquor), "jirnarri" (food), and "mangarri" (vegetable). In other cases, select "kuapyti".
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
**muru-pinyi walya (Eng: insert in the ground)

* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common.
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)

* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T04:12:33Z

Cpillsb1: /* wbp → gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
** Rule: select "mboy'u" if "muru-pinyi" is followed by food or drink words: "ngapa" (water/grog), "pama" (liquor), "jirnarri" (food), and "mangarri" (vegetable). In other cases, select "kuapyti".
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
**muru-pinyi walya (Eng: insert in the ground)

* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common.
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)

* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.

* (wbp) warlu → (gug) tini "hot"; aku "angry"
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.

* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.

* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.

* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T04:07:04Z

Cpillsb1: /* wbp → gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
** Rule: select "mboy'u" if "muru-pinyi" is followed by food or drink words: "ngapa" (water/grog), "pama" (liquor), "jirnarri" (food), and "mangarri" (vegetable). In other cases, select "kuapyti".
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
**muru-pinyi walya (Eng: insert in the ground)

* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common.
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)

* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi".
* (wbp) warlu → (gug) tini "hot"; aku "angry"
**miparrpa = face or person; yapa = person
* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
**watiya = plant

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** marnilpa - hair
* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
**jarntu = dog; mangarri = fruit
* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
**yangkarni = to wear

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T02:58:15Z

Cpillsb1: /* wbp → gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====6 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.

* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.

* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "??" (Eng: letter). Otherwise, select "nyinanja-wantimi" as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$





===wbp → gug===
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
** Rule: select "mboy'u" if "muru-pinyi" is followed by food or drink words: "ngapa" (water/grog), "pama" (liquor), "jirnarri" (food), and "mangarri" (vegetable). In other cases, select "kuapyti".
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
**muru-pinyi walya (Eng: insert in the ground)

* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common.
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)

* (wbp) nyurltu-nyurltu → (gug) ADD HERE "confusing, garbled"; ADD HERE "tangled"
** marnilpa - hair
* (wbp) warlu → (gug) tini "hot"; aku "angry"
**miparrpa = face or person; yapa = person
* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
**watiya = plant

* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
** marnilpa - hair
* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
**jarntu = dog; mangarri = fruit
* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
**yangkarni = to wear

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-20T02:01:47Z

Cpillsb1: /* wbp → gug */

Resources for machine translation between [https://wikis.swarthmore.edu/ling073/Guarani Guarani] and [https://wikis.swarthmore.edu/ling073/Warlpiri Warlpiri]

==Corpora==
*[https://www.bible.com/bible/1355/rev.1 Warlpiri Bible]

*[https://www.bible.com/bible/66/rev.1 Guarani Bible]

*[https://www.bible.com/bible/111/rev.1 English Bible]

*[http://unicode.org/udhr/d/udhr_gug.txt Universal Declaration of Human Rights in Guarani]

==Developed Resources==
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp-corpus Corpus Repository]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Contrastive_Grammar Contrastive Grammar]
*[https://github.swarthmore.edu/tjones5/ling073-gug-wbp Guarani to Warlpiri analyzer repository]
**This repo will hold the fully functioning rule-based machine translation system.
*[https://github.swarthmore.edu/cpillsb1/ling073-wbp-gug Warlpiri to Guarani analyzer repository]
**This repo will not be developed further.
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Lexical_selection Lexical selection Wiki page]
*[https://wikis.swarthmore.edu/ling073/Guarani_and_Warlpiri/Structural_transfer Structural transfer Wiki page]

==Lexical Selection==
* See Lexical Selection page linked above for more detail

* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
* (wbp) rdaka → (gug) avatisoka "hand"; po "five"
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

==Initial Evaluation==
===wbp → gug evaluation===
====Results when running on tests====
*Total number of words: 14
*Total number of unknown words: 4
*Percentage of unknown words: 28.57%
*Percentage of stems translated correctly: 71.43%

When removing unknown words:
*WER = 78.57%
*PER = 78.57%
When unknown words are not removed:
*WER = 100%
*PER = 100%

====Results when running on sentences (corpus) ====
*Total number of words: 58
*Total number of unknown words: 68
*Percentage of unknown words: 84.45%
*Percentage of stems translate correctly: 15.52%

When removing unknown words:
*WER = 22.41%
*PER = 22.41%
When unknown words are not removed:
*WER = 100%
*PER = 100%

===gug → wbp evaluation===
====Results when running on tests====
*Total number of words: 13
*Total number of unknown words: 0
*Percentage of unknown words: 0%
*Percentage of stems translated correctly: 100%

When removing unknown words:
*WER = 92.86%
*PER = 92.86%
When unknown words are not removed:
*WER = 92.86%
*PER = 92.86%

====Results when running on sentences (corpus) ====
*Total number of words: 66
*Total number of unknown words: 60
*Percentage of unknown words: 90.9%
*Percentage of stems translated correctly: 9.09%

When removing unknown words:
*WER = 0.0%
*PER = 0.0%
When unknown words are not removed:
*WER = 100%
*PER = 100%

==Final Evaluation==

===gug → wbp and wbp → gug===
====100 more stems====
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

===gug → wbp===

====3 new lexical selection rules====
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.

* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.

* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.

====6 additions to the morphology====
*Added numeral analysis:
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
**the -pala ending distinguishes them as number words, but it is not always necessary
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$

*Added adverb analysis:
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$

*Added elative/source case for verb auxiliaries :
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$

*Added inceptive aspect for verbs:
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$

*Added possessive marker "nyanu" for nouns:
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$

*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$



====4 new disambiguation rules====
*Number vs Noun (e.g. rdaka = hand or five), has the number marker -pala
*Manu = cnjcoo vs v tv past?
*Kuja = "ka" vaux rel subj3sg OR kuja = kuja cj. relative pronoun, what, which, that, who.
**Kuja = "ka" vaux rel subj3sg OR kuja = kuja cj. relative pronoun, what, which, that, who.
**Ngula = "ka" vaux rel subj3sg OR kuja = kuja cj. relative pronoun, what, which, that, who. Find by searching AUX:COMP in new dictionary

===wbp → gug===
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
** Rule: select "mboy'u" if "muru-pinyi" is followed by food or drink words: "ngapa" (water/grog), "pama" (liquor), "jirnarri" (food), and "mangarri" (vegetable). In other cases, select "kuapyti".
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
**muru-pinyi walya (Eng: insert in the ground)

* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common.
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)

* (wbp) nyurltu-nyurltu → (gug) ADD HERE "confusing, garbled"; ADD HERE "tangled"
** hair
* (wbp) warlu → (gug) tini "hot"; aku "angry"
**miparrpa = face or person; yapa = person
* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
**watiya = plant

[[Category:Sp17_TranslationPairs]]

Guarani and Warlpiri

2017-04-18T03:10:19Z

Cpillsb1: /* 3 new lexical selection rules */

Guarani and Warlpiri

2017-04-18T02:28:45Z

Cpillsb1: /* wbp → gug */

Guarani and Warlpiri

2017-04-18T02:24:16Z

Cpillsb1: /* 3 new lexical selection rules */

Guarani and Warlpiri/Structural transfer

2017-04-07T02:59:36Z

Cpillsb1: /* Structural Transfer Rule */

==Pre-Evaluation==

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 113.79 %
*Position-independent word error rate (PER): 113.79 %

===wbp → gug===
Results when running on gug.sentences.txt:
*Word error rate (WER): 100.0 %
*Position-independent word error rate (PER): 100.0 %

==Structural Transfer Rule==

===gug → wbp===
*Sample sentence: mitã okaru → kurdu ka ngarni
*tagger: ^mitã<n><sg><subj>$ ^karu<v><tv><ar><pres><p3><sp>$^.<sent>$
*biltrans: ^mitã<n><sg><subj>/kurdu<n><sg><subj>$ ^karu<v><tv><ar><pres><p3><sp>/ngarni<v><tv><ar><pres><p3><sp>$^.<sent>/.<sent>$
*chunker:
**apertium-transfer: Rule 2 mitã<n><sg><subj>/kurdu<n><sg><subj>
**apertium-transfer: Rule 3 karu<v><tv><ar><pres><p3><sp>/ngarni<v><tv><ar><pres><p3><sp>
**apertium-transfer: Rule 1 .<sent>/.<sent> ^n<SN><sg><subj>{^kurdu<n><2>$}$ ^vaux<Saux><SubjTBD>{^ka<vaux><pres><2>$}$ ^v<SV>{^ngarni<v><tv><pres>$}$^sent<SENT>{^.<sent>$}$
*postchunk: ^kurdu<n><sg>$ ^ka<vaux><pres><subj3sg>$ ^ngarni<v><tv><pres>$^.<sent>$
*gug-wbp: #kurdu #ka #ngarni# (there is a lingering issue in my generator)

===wbp → gug===
*Sample sentence: kurdu ka ngarni → mitã okaru
*tagger: ^kurdu<n><sg><abs>$ ^ka<vaux><pres><subj3sg>$ ^ngarni<v><tv><pres>$^.<sent>$
*biltrans: ^kurdu<n><sg><abs>/mitã<n><sg><abs>$ ^ka<vaux><pres><subj3sg>/<pres><subj3sg>$ ^ngarni<v><tv><pres>/karu<v><tv><ar><pres>$^.<sent>/.<sent>$
*chunker:
**apertium-transfer: Rule 2 ka<vaux><pres><subj3sg>/<pres><subj3sg> ngarni<v><tv><pres>/karu<v><tv><ar><pres>
**apertium-transfer: Rule 1 .<sent>/.<sent>
*interchunk: ^default<default>{^mitã<n><sg><abs>$}$ ^sent<v>{^karu<v><tv><ar><pres><p3><sp>$}$^sent<SENT>{^.<sent>$}$
*postchunk: ^mitã<n><sg><abs>$ ^karu<v><tv><ar><pres><p3><sp>$^.<sent>$
*wbp-gug: #mitã okaru (need a transfer rule for nouns to add the subject tag and remove abs tag)

==Post-Evaluation==

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 115.52 %
*Position-independent word error rate (PER): 115.52 %

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 100.00 %
*Position-independent word error rate (PER): 100.00 %
(I think nouns are not translating correctly anymore after adding the <subj> tags to them. Will try to fix by next week)

[[Category:Sp17_StructuralTransfer]]

Guarani and Warlpiri/Structural transfer

2017-04-07T02:55:11Z

Cpillsb1: /* gug → wbp */

==Pre-Evaluation==

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 113.79 %
*Position-independent word error rate (PER): 113.79 %

===wbp → gug===
Results when running on gug.sentences.txt:
*Word error rate (WER): 100.0 %
*Position-independent word error rate (PER): 100.0 %

==Structural Transfer Rule==

===gug → wbp===
*Sample sentence: mitã okaru → kurdu ka ngarni
*tagger: ^mitã<n><sg><subj>$ ^karu<v><tv><ar><pres><p3><sp>$^.<sent>$
*biltrans: ^mitã<n><sg><subj>/kurdu<n><sg><subj>$ ^karu<v><tv><ar><pres><p3><sp>/ngarni<v><tv><ar><pres><p3><sp>$^.<sent>/.<sent>$
*chunker:
**apertium-transfer: Rule 2 mitã<n><sg><subj>/kurdu<n><sg><subj>
**apertium-transfer: Rule 3 karu<v><tv><ar><pres><p3><sp>/ngarni<v><tv><ar><pres><p3><sp>
**apertium-transfer: Rule 1 .<sent>/.<sent> ^n<SN><sg><subj>{^kurdu<n><2>$}$ ^vaux<Saux><SubjTBD>{^ka<vaux><pres><2>$}$ ^v<SV>{^ngarni<v><tv><pres>$}$^sent<SENT>{^.<sent>$}$
*postchunk: ^kurdu<n><sg>$ ^ka<vaux><pres><subj3sg>$ ^ngarni<v><tv><pres>$^.<sent>$
*gug-wbp: #kurdu #ka #ngarni# (there is a lingering issue in my generator)

===wbp → gug===
*add ar, air, chen tags to dix
*do reverse of previous steps

==Post-Evaluation==

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 115.52 %
*Position-independent word error rate (PER): 115.52 %

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 100.00 %
*Position-independent word error rate (PER): 100.00 %
(I think nouns are not translating correctly anymore after adding the <subj> tags to them. Will try to fix by next week)

[[Category:Sp17_StructuralTransfer]]

Guarani and Warlpiri/Structural transfer

2017-04-07T02:54:23Z

Cpillsb1: /* wbp → gug */

Guarani and Warlpiri/Structural transfer

2017-04-07T02:53:00Z

Cpillsb1: /* Post-Evaluation */

==Pre-Evaluation==

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 113.79 %
*Position-independent word error rate (PER): 113.79 %

===wbp → gug===
Results when running on gug.tests.txt:
*Word error rate (WER): 83.33 %
*Position-independent word error rate (PER): 83.33 %

Results when running on gug.sentences.txt:
*Word error rate (WER): 100.0 %
*Position-independent word error rate (PER): 100.0 %

(I think the WER and PER got worse because nouns are no longer translating correctly after adding the <subj> tag to all nouns and pronouns).

==Structural Transfer Rule==

===gug → wbp===
*Sample sentence: mitã okaru → kurdu ka ngarni
*tagger: ^mitã<n><sg><subj>$ ^karu<v><tv><ar><pres><p3><sp>$^.<sent>$
*biltrans: ^mitã<n><sg><subj>/kurdu<n><sg><subj>$ ^karu<v><tv><ar><pres><p3><sp>/ngarni<v><tv><ar><pres><p3><sp>$^.<sent>/.<sent>$
*chunker:
**apertium-transfer: Rule 2 mitã<n><sg><subj>/kurdu<n><sg><subj>
**apertium-transfer: Rule 3 karu<v><tv><ar><pres><p3><sp>/ngarni<v><tv><ar><pres><p3><sp>
**apertium-transfer: Rule 1 .<sent>/.<sent> ^n<SN><sg><subj>{^kurdu<n><2>$}$ ^vaux<Saux><SubjTBD>{^ka<vaux><pres><2>$}$ ^v<SV>{^ngarni<v><tv><pres>$}$^sent<SENT>{^.<sent>$}$
*postchunk: ^kurdu<n><sg>$ ^ka<vaux><pres><subj3sg>$ ^ngarni<v><tv><pres>$^.<sent>$
*gug-wbp: #kurdu #ka #ngarni# (there is a lingering issue in my generator)

===wbp → gug===
*add ar, air, chen tags to dix
*do reverse of previous steps

==Post-Evaluation==

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 115.52 %
*Position-independent word error rate (PER): 115.52 %

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 100.00 %
*Position-independent word error rate (PER): 100.00 %

[[Category:Sp17_StructuralTransfer]]

Guarani and Warlpiri/Structural transfer

2017-04-07T02:49:30Z

Cpillsb1: /* Pre-Evaluation */

==Pre-Evaluation==

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 113.79 %
*Position-independent word error rate (PER): 113.79 %

===wbp → gug===
Results when running on gug.tests.txt:
*Word error rate (WER): 83.33 %
*Position-independent word error rate (PER): 83.33 %

Results when running on gug.sentences.txt:
*Word error rate (WER): 100.0 %
*Position-independent word error rate (PER): 100.0 %

(I think the WER and PER got worse because nouns are no longer translating correctly after adding the <subj> tag to all nouns and pronouns).

==Structural Transfer Rule==

===gug → wbp===
*Sample sentence: mitã okaru → kurdu ka ngarni
*tagger: ^mitã<n><sg><subj>$ ^karu<v><tv><ar><pres><p3><sp>$^.<sent>$
*biltrans: ^mitã<n><sg><subj>/kurdu<n><sg><subj>$ ^karu<v><tv><ar><pres><p3><sp>/ngarni<v><tv><ar><pres><p3><sp>$^.<sent>/.<sent>$
*chunker:
**apertium-transfer: Rule 2 mitã<n><sg><subj>/kurdu<n><sg><subj>
**apertium-transfer: Rule 3 karu<v><tv><ar><pres><p3><sp>/ngarni<v><tv><ar><pres><p3><sp>
**apertium-transfer: Rule 1 .<sent>/.<sent> ^n<SN><sg><subj>{^kurdu<n><2>$}$ ^vaux<Saux><SubjTBD>{^ka<vaux><pres><2>$}$ ^v<SV>{^ngarni<v><tv><pres>$}$^sent<SENT>{^.<sent>$}$
*postchunk: ^kurdu<n><sg>$ ^ka<vaux><pres><subj3sg>$ ^ngarni<v><tv><pres>$^.<sent>$
*gug-wbp: #kurdu #ka #ngarni# (there is a lingering issue in my generator)

===wbp → gug===
*add ar, air, chen tags to dix
*do reverse of previous steps

==Post-Evaluation==

===gug → wbp ===
Results when running on gug.sentences.txt:
*Word error rate (WER): 115.52 %
*Position-independent word error rate (PER): 115.52 %

[[Category:Sp17_StructuralTransfer]]

Guarani and Warlpiri/Lexical selection

2017-03-31T01:34:55Z

Cpillsb1: /* wbp → gug */

==gug → wbp==
* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
** Rule: Select "lirra" (Eng: voice) as the translation of "ahy'o" when it is followed by "tyapu" (Eng: loud) or "kirirĩ" (Eng: quiet). Select "ngukarna" (Eng: throat) as the translation of "ahy'o" when it is followed by "rasy" (Eng: sore). Otherwise, select "lirra" as the default.
** Ha'e ahy'o tyapu ("His/Her loud voice")
** Ha'e oguereko ahy'o rasy ("He/she/they have a sore throat")

* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
** Rule: Select "japirdimi" (Eng: collar) as the translation of "ajúra" when it is followed by color words such as "pytã" (Eng: red), "chovy" (Eng: blue) or "aky" (Eng: green). Select "waninja" (Eng: neck) as the translation of "ajúra" when it is followed by "puku" (Eng: long) or "koli" (Eng: short). Otherwise, select "waninja" as the default.
** Ajúra puku ("long neck")
** Ajúra pytã ("red collar")

==wbp → gug==
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
** Rule: select "mboy'u" if "muru-pinyi" is followed by food or drink words: "ngapa" (water/grog), "pama" (liquor), "jirnarri" (food), and "mangarri" (vegetable). In other cases, select "kuapyti".
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
**muru-pinyi walya (Eng: insert in the ground)

* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common.
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)




[[Category:Sp17_LexicalSelection]]

Guarani and Warlpiri/Lexical selection

2017-03-31T01:02:16Z

Cpillsb1: /* wbp → gug */

==gug → wbp==
* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
** Rule: Select "lirra" (Eng: voice) as the translation of "ahy'o" when it is followed by "tyapu" (Eng: loud) or "kirirĩ" (Eng: quiet). Select "ngukarna" (Eng: throat) as the translation of "ahy'o" when it is followed by "rasy" (Eng: sore). Otherwise, select "lirra" as the default.
** Ha'e ahy'o tyapu ("His/Her loud voice")
** Ha'e oguereko ahy'o rasy ("He/she/they have a sore throat")

* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
** Rule: Select "japirdimi" (Eng: collar) as the translation of "ajúra" when it is followed by color words such as "pytã" (Eng: red), "BLUE" (Eng: blue) or "GREEN" (Eng: green). Select "waninja" (Eng: neck) as the translation of "ajúra" when it is followed by "puku" (Eng: long) or "koli" (Eng: short). Otherwise, select "waninja" as the default.
** Ajúra puku ("long neck")
** Ajúra pytã ("red collar")

==wbp → gug==
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
** Rule: select "mboy'u" if "muru-pinyi" is followed by "ngapa" (water/grog)
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
**muru-pinyi walya (Eng: insert in the ground)

* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common.
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)




[[Category:Sp17_LexicalSelection]]

Guarani and Warlpiri/Lexical selection

2017-03-31T01:02:02Z

Cpillsb1: /* wbp → gug */

==gug → wbp==
* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
** Rule: select "lirra" if "ahy'o" is followed by "tyapu" (loud)
** Ha'e ahy'o tyapu ("His/Her loud voice")
** Ha'e oguereko ahy'o rasy ("He/she/they have a sore throat")

* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
** Rule: select "waninja" as the default
** Ajúra puku ("long neck")
** Ajúra pytã ("red collar")

==wbp → gug==
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
** Rule: select "mboy'u" if "muru-pinyi" is followed by "ngapa" (water/grog)
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
**muru-pinyi walya (Eng: insert in the ground)

* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)




[[Category:Sp17_LexicalSelection]]