Difference between revisions of "Bikol and Chamorro"

From LING073
Jump to: navigation, search
 
(29 intermediate revisions by 2 users not shown)
Line 1: Line 1:
 
Resources for machine translation between Bikol and Chamorro
 
Resources for machine translation between Bikol and Chamorro
 +
* [https://github.swarthmore.edu/ltarlin1/ling073-bcl-cha Final Bikol-Chamorro translation repository]
 
* [https://wikis.swarthmore.edu/ling073/Bikol Bikol]
 
* [https://wikis.swarthmore.edu/ling073/Bikol Bikol]
 
* [https://wikis.swarthmore.edu/ling073/Chamorro Chamorro]
 
* [https://wikis.swarthmore.edu/ling073/Chamorro Chamorro]
Line 5: Line 6:
 
== Developed Resources ==
 
== Developed Resources ==
 
* [https://wikis.swarthmore.edu/ling073/Bikol_and_Chamorro/Contrastive_Grammar Contrastive Grammar]
 
* [https://wikis.swarthmore.edu/ling073/Bikol_and_Chamorro/Contrastive_Grammar Contrastive Grammar]
 +
* [https://wikis.swarthmore.edu/ling073/Bikol_and_Chamorro/Lexical_Selection Lexical Selection]
  
 
== Translation Repositories ==
 
== Translation Repositories ==
 
* [https://github.swarthmore.edu/ltarlin1/ling073-bcl-cha Bikol to Chamorro translation]
 
* [https://github.swarthmore.edu/ltarlin1/ling073-bcl-cha Bikol to Chamorro translation]
 
* [https://github.swarthmore.edu/eortici1/ling073-cha-bcl Chamorro to Bikol translation]
 
* [https://github.swarthmore.edu/eortici1/ling073-cha-bcl Chamorro to Bikol translation]
 +
 +
== Initial Evaluation ==
 +
=== bcl → cha Evalutaion ===
 +
* WER = 94.74%
 +
* PER = 84.21%
 +
* Proportion of stems translated correctly = 100.00%
 +
 +
=== cha → bcl Evaluation ===
 +
* WER = 90.91%
 +
* PER = 86.36%
 +
* Proportion of stems translated correctly = 100.00%
 +
 +
=== Lexical Selection ===
 +
Find at least two cases in each direction of a one-to-many mapping.
 +
 +
==== Bikol-Chamorro ====
 +
===== bóla =====
 +
In Bikol, <b>bóla</b> means ball or compliment. In Chamorro, ball = <i>bola</i> and compliment = <i>komplimenta</i>.
 +
 +
Lexical selection between bola and komplimenta is guided by the following rules:
 +
* Bola (ball) is chosen when:
 +
** Preceded by a verb such as throw, toss, catch, play, buy, borrow, lend, bounce
 +
** Followed by an adjective such as round, colors
 +
 +
Example sentences
 +
* Bola (ball) is chosen in the following example:
 +
** Sublion mo si bola ki Jose (<u>Borrow</u> the <i>ball</i> from Jacob)
 +
* Komplimenta (compliment) is chosen in the following example:
 +
** <example here>
 +
 +
===== glóbo =====
 +
In Bikol, <b>glóbo</b> means map or balloon. In Chamorro, map = <i>mapa</i> and balloon = <i>abubu</i>.
 +
 +
For now, the default selection is set to translate glóbo to abubu, or balloon in English.
 +
 +
==== Chamorro-Bikol ====
 +
* In Chamorro, <b>guakse</b> means to scrub (clothes) or to turn inside out. In Bikol, to scrub (clothes) is <i>kuró-kusó</i> and to turn inside out is <i>balík</i>.
 +
* <b>maggem</b> means cautious or damp. In Bikol, <i>máan</i> means cautious and <i>basá</i> means damp.
 +
 +
 +
=== Structural Transfer ===
 +
*[https://wikis.swarthmore.edu/ling073/Bikol_and_Chamorro/Structural_transfer Structural Transfer wiki]
 +
 +
== Final Evaluation ==
 +
 +
=== Polished RBMT System ===
 +
 +
==== Bcl-Cha ====
 +
===== Additional Stems =====
 +
* 100 additional stems (verbs, adjectives, and nouns) were added to the bilingual dictionaries and both monolingual dictionaries.
 +
===== Lexical Selection Rules =====
 +
* In Bikol, the adjective <i>sadít</i> can either mean (1) small, tiny; or (2) low (as a soft voice).
 +
** <i>Despasio</i> (low, soft) is chosen if the adjective <i>sadít</i> follows the noun <i>bóses</i>, or voice.
 +
** <i>Balaskes</i> (small, tiny) is the default and is chosen in all other circumstances.
 +
 +
* In Bikol,
 +
** <i>Pasífiku</i> (Pacific) is chosen if the adjective <i>pasípiko</i> is in the exact phrase <i>dágat na pasípiko</i>, or Pacific Ocean.
 +
** <i>Mahgong</i> (peaceful) is the default and is chosen in all other circumstances.
 +
 +
==== Bcl Transducer ====
 +
===== Disambiguation (x2) =====
 +
====== sa ======
 +
The Bikol word "sa" can have either of the following two meanings, illustrated by the following example sentences.
 +
* <u>Determiner</u>: the
 +
** Nagdumán akó sa haróng na dakúla. <i>(I went to the big house.)</i>
 +
** Correct analysis: <code>^Nagdumán/dumán<vblex><past>$ ^akó/akó<prn><p1><sg>$ ^sa<det><def>$ ^haróng/haróng<n>$ ^na/na<link>$ ^dakúla<adj><sg>$^./.<sent>$</code>
 +
* <u>Preposition</u>: to
 +
** Nagdumán akó sa Píli. <i>(I went to Píli.)</i>
 +
** Correct analysis: <code>^Nagdumán/dumán<vblex><past>$ ^akó/akó<prn><p1><sg>$ ^sa/sa<pr>$ ^Píli/Píli<cog>$^./.<sent>$</code>
 +
 +
====== dakúla ======
 +
The Bikol word "dakúla" can have either of the following two meanings, illustrated by the following example sentences.
 +
* <u>Adjective</u>: big
 +
** Nagdumán akó sa haróng na dakúla. <i>(I went to the big house.)</i>
 +
** Correct analysis: <code>^Nagdumán/dumán<vblex><past>$ ^akó/akó<prn><p1><sg>$ ^sa/sa<det><def>$ ^haróng/haróng<n>$ ^na/na<link>$ ^dakúla<adj><sg>$^./.<sent>$</code>
 +
* <u>Verb</u>: to grow bigger
 +
** Dakúla an búrak. <i>(A flower grows.)</i>
 +
** Correct analysis: <code>^dakúla/dakúla<vblex>$ ^an/an<det><ind>$ ^búrak/búrak<n>$^./.<sent>$</code>
 +
 +
 +
<!--
 +
== List of extra words ==
 +
Nouns:
 +
*basúra: garbage
 +
*garáhe: garage <-------didnʼt have
 +
*matemátika: mathematics
 +
*dungó: nose
 +
*pasénsia: patience
 +
*bolsá: pocket
 +
*hílo: poison
 +
*lamésa: table
 +
*pábo: turkey
 +
*dága: knife
 +
*púso: heart
 +
*lalawgón: face
 +
*kolór: color
 +
*kapé: coffee
 +
*báybáy: coast
 +
*bádo: clothes
 +
*inápay: bread
 +
 +
Verbs:
 +
*luwás: to exit, to leave
 +
*apód: to call (someone)
 +
*sublí: to borrow
 +
*hatód: to bring, to deliver
 +
*será: to close
 +
*kagrít: to scream
 +
*bakál: to shop <-------didnʼt have
 +
*tarám: to talk
 +
*halát: to wait
 +
*matá: to wake up
 +
*búhay: to live
 +
*taó: to give
 +
*dekorár: to decorate
 +
*bítbít: to carry
 +
 +
== Other possible lexical selection options ==
 +
* bulan: moon, month (110)
 +
* dali (ma-): quickly, easily (123)
 +
* dampog: foggy, moist (124)
 +
* delikado: delicate, dangerous (129)
 +
* duros (ma-): windy, breezy; boastful *** guaifon,
 +
* gabat: heavy, grievous (154)
 +
* gana: enthusiasm, appetite (156)
 +
* grado: grade (temp.) and grade (1st grade) (164)
 +
gugu (165)
 +
gurano (167)
 +
gusto (168)
 +
gutos (169)
 +
 +
== Notes for Evan ==
 +
* typo in first line of Test 1 - Chamorro word should be "linulí"
 +
* is the accent supposed to be over the > sign? Is that just a weird rendering thing that doesn't actually matter?
 +
* Test 2 line 2 - the root is actually "gumaʼ", weʼll add the suffix and vowel change in a later step
 +
* Test 3 line 1 - accent looks like it's in the wrong place on maéstro
 +
* Test 3 line 1 - again, the root is just "maʼestro" and the prefix will be added later
 +
* Test 5 line 1 - root is "metgot"
 +
* I put all the above words (except "garage" and "to shop") into the bcl-cha dix file. Youʼll have to put them in the cha-bcl file (unless you did already) the same way but switched left and right. We also have to add them to our respective lexc files eventually as well
 +
 +
== Notes for Lee ==
 +
* Test 1, iinulí should be ulí
 +
* Test 4, nagdumán should be dumán
 +
* Test 5, makusóg should be kusóg
 +
 +
-->
  
 
[[Category:Sp17_TranslationPairs]]
 
[[Category:Sp17_TranslationPairs]]

Latest revision as of 22:43, 3 May 2017

Resources for machine translation between Bikol and Chamorro

Developed Resources

Translation Repositories

Initial Evaluation

bcl → cha Evalutaion

  • WER = 94.74%
  • PER = 84.21%
  • Proportion of stems translated correctly = 100.00%

cha → bcl Evaluation

  • WER = 90.91%
  • PER = 86.36%
  • Proportion of stems translated correctly = 100.00%

Lexical Selection

Find at least two cases in each direction of a one-to-many mapping.

Bikol-Chamorro

bóla

In Bikol, bóla means ball or compliment. In Chamorro, ball = bola and compliment = komplimenta.

Lexical selection between bola and komplimenta is guided by the following rules:

  • Bola (ball) is chosen when:
    • Preceded by a verb such as throw, toss, catch, play, buy, borrow, lend, bounce
    • Followed by an adjective such as round, colors

Example sentences

  • Bola (ball) is chosen in the following example:
    • Sublion mo si bola ki Jose (Borrow the ball from Jacob)
  • Komplimenta (compliment) is chosen in the following example:
    • <example here>
glóbo

In Bikol, glóbo means map or balloon. In Chamorro, map = mapa and balloon = abubu.

For now, the default selection is set to translate glóbo to abubu, or balloon in English.

Chamorro-Bikol

  • In Chamorro, guakse means to scrub (clothes) or to turn inside out. In Bikol, to scrub (clothes) is kuró-kusó and to turn inside out is balík.
  • maggem means cautious or damp. In Bikol, máan means cautious and basá means damp.


Structural Transfer

Final Evaluation

Polished RBMT System

Bcl-Cha

Additional Stems
  • 100 additional stems (verbs, adjectives, and nouns) were added to the bilingual dictionaries and both monolingual dictionaries.
Lexical Selection Rules
  • In Bikol, the adjective sadít can either mean (1) small, tiny; or (2) low (as a soft voice).
    • Despasio (low, soft) is chosen if the adjective sadít follows the noun bóses, or voice.
    • Balaskes (small, tiny) is the default and is chosen in all other circumstances.
  • In Bikol,
    • Pasífiku (Pacific) is chosen if the adjective pasípiko is in the exact phrase dágat na pasípiko, or Pacific Ocean.
    • Mahgong (peaceful) is the default and is chosen in all other circumstances.

Bcl Transducer

Disambiguation (x2)
sa

The Bikol word "sa" can have either of the following two meanings, illustrated by the following example sentences.

  • Determiner: the
    • Nagdumán akó sa haróng na dakúla. (I went to the big house.)
    • Correct analysis: ^Nagdumán/dumán<vblex><past>$ ^akó/akó<prn><p1><sg>$ ^sa<det><def>$ ^haróng/haróng<n>$ ^na/na<link>$ ^dakúla<adj><sg>$^./.<sent>$
  • Preposition: to
    • Nagdumán akó sa Píli. (I went to Píli.)
    • Correct analysis: ^Nagdumán/dumán<vblex><past>$ ^akó/akó<prn><p1><sg>$ ^sa/sa<pr>$ ^Píli/Píli<cog>$^./.<sent>$
dakúla

The Bikol word "dakúla" can have either of the following two meanings, illustrated by the following example sentences.

  • Adjective: big
    • Nagdumán akó sa haróng na dakúla. (I went to the big house.)
    • Correct analysis: ^Nagdumán/dumán<vblex><past>$ ^akó/akó<prn><p1><sg>$ ^sa/sa<det><def>$ ^haróng/haróng<n>$ ^na/na<link>$ ^dakúla<adj><sg>$^./.<sent>$
  • Verb: to grow bigger
    • Dakúla an búrak. (A flower grows.)
    • Correct analysis: ^dakúla/dakúla<vblex>$ ^an/an<det><ind>$ ^búrak/búrak<n>$^./.<sent>$
Retrieved from "http://wikis.swarthmore.edu/ling073/index.php?title=Bikol_and_Chamorro&oldid=5017"