http://wikis.swarthmore.edu/ling073/api.php?action=feedcontributions&feedformat=atom&user=Cayoh1 2026-10-25T10:19:31Z User contributions MediaWiki 1.27.7 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14695 2021-05-20T20:55:38Z

<p>Cayoh1: /* Outline */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added nouns, verbs, pronouns, adjectives, and interjections, and conjunctions to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools and the lack of a standard orthography for the language. Yoruba is a tonal language and has many characters in the vocabulary are accented and can be written differently depending on which region you learned the language in. This has led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|thumb| Vowels Used in Yoruba]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> To evaluate my transducer, I tested coverage over two large corpuses in Yoruba; Wikipedia and the Bible.<br /> <br /> === Wikipedia ===<br /> <br /> TOP UNKNOWN WORDS:<br /> 26244 ^ni/*ni$<br /> 18828 ^tí/*tí$<br /> 16783 ^ti/*ti$<br /> 16252 ^ní/*ní$<br /> 9895 ^àwọn/*àwọn$<br /> 7621 ^àti/*àti$<br /> 7503 ^je/*je$<br /> 7093 ^jẹ́/*jẹ́$<br /> 6521 ^ń/*ń$<br /> 6085 ^ati/*ati$<br /> 5680 ^rẹ̀/*rẹ̀$<br /> 5556 ^sí/*sí$<br /> 5458 ^ọdún/*ọdún$<br /> 5237 ^to/*to$<br /> 5182 ^wọ́n/*wọ́n$<br /> 4846 ^èdè/*èdè$<br /> 4768 ^ṣe/*ṣe$<br /> 4717 ^the/*the$<br /> 4697 ^fún/*fún$<br /> 4513 ^of/*of$<br /> coverage: 287237 / 1283498 (~0.22379232379014225188)<br /> <br /> remaining unknown forms: 996261<br /> <br /> === The Bible ===<br /> TOP UNKNOWN WORDS:<br /> 9572 ^si/*si$<br /> 8152 ^ti/*ti$<br /> 3724 ^awọn/*awọn$<br /> 3530 ^ni/*ni$<br /> 3405 ^fun/*fun$<br /> 3204 ^li/*li$<br /> 3051 ^ki/*ki$<br /> 2841 ^ati/*ati$<br /> 2534 ^rẹ̀/*rẹ̀$<br /> 2412 ^nwọn/*nwọn$<br /> 2069 ^pe/*pe$<br /> 1965 ^nyin/*nyin$<br /> 1927 ^fi/*fi$<br /> 1872 ^bi/*bi$<br /> 1649 ^ninu/*ninu$<br /> 1648 ^ba/*ba$<br /> 1588 ^kò/*kò$<br /> 1506 ^ṣe/*ṣe$<br /> 1379 ^Ọlọrun/*Ọlọrun$<br /> 1278 ^lati/*lati$<br /> coverage: 53863 / 233959 (~0.23022409909428575092)<br /> <br /> remaining unknown forms: 180096<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14694 2021-05-20T20:53:34Z

<p>Cayoh1: /* Wikipedia */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools and the lack of a standard orthography for the language. Yoruba is a tonal language and has many characters in the vocabulary are accented and can be written differently depending on which region you learned the language in. This has led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|thumb| Vowels Used in Yoruba]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> To evaluate my transducer, I tested coverage over two large corpuses in Yoruba; Wikipedia and the Bible.<br /> <br /> === Wikipedia ===<br /> <br /> TOP UNKNOWN WORDS:<br /> 26244 ^ni/*ni$<br /> 18828 ^tí/*tí$<br /> 16783 ^ti/*ti$<br /> 16252 ^ní/*ní$<br /> 9895 ^àwọn/*àwọn$<br /> 7621 ^àti/*àti$<br /> 7503 ^je/*je$<br /> 7093 ^jẹ́/*jẹ́$<br /> 6521 ^ń/*ń$<br /> 6085 ^ati/*ati$<br /> 5680 ^rẹ̀/*rẹ̀$<br /> 5556 ^sí/*sí$<br /> 5458 ^ọdún/*ọdún$<br /> 5237 ^to/*to$<br /> 5182 ^wọ́n/*wọ́n$<br /> 4846 ^èdè/*èdè$<br /> 4768 ^ṣe/*ṣe$<br /> 4717 ^the/*the$<br /> 4697 ^fún/*fún$<br /> 4513 ^of/*of$<br /> coverage: 287237 / 1283498 (~0.22379232379014225188)<br /> <br /> remaining unknown forms: 996261<br /> <br /> === The Bible ===<br /> TOP UNKNOWN WORDS:<br /> 9572 ^si/*si$<br /> 8152 ^ti/*ti$<br /> 3724 ^awọn/*awọn$<br /> 3530 ^ni/*ni$<br /> 3405 ^fun/*fun$<br /> 3204 ^li/*li$<br /> 3051 ^ki/*ki$<br /> 2841 ^ati/*ati$<br /> 2534 ^rẹ̀/*rẹ̀$<br /> 2412 ^nwọn/*nwọn$<br /> 2069 ^pe/*pe$<br /> 1965 ^nyin/*nyin$<br /> 1927 ^fi/*fi$<br /> 1872 ^bi/*bi$<br /> 1649 ^ninu/*ninu$<br /> 1648 ^ba/*ba$<br /> 1588 ^kò/*kò$<br /> 1506 ^ṣe/*ṣe$<br /> 1379 ^Ọlọrun/*Ọlọrun$<br /> 1278 ^lati/*lati$<br /> coverage: 53863 / 233959 (~0.23022409909428575092)<br /> <br /> remaining unknown forms: 180096<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14693 2021-05-20T20:53:24Z

<p>Cayoh1: /* The Bible */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools and the lack of a standard orthography for the language. Yoruba is a tonal language and has many characters in the vocabulary are accented and can be written differently depending on which region you learned the language in. This has led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|thumb| Vowels Used in Yoruba]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> To evaluate my transducer, I tested coverage over two large corpuses in Yoruba; Wikipedia and the Bible.<br /> <br /> === Wikipedia ===<br /> <br /> TOP UNKNOWN WORDS:<br /> 26244 ^ni/*ni$<br /> 18828 ^tí/*tí$<br /> 16783 ^ti/*ti$<br /> 16252 ^ní/*ní$<br /> 9895 ^àwọn/*àwọn$<br /> 7621 ^àti/*àti$<br /> 7503 ^je/*je$<br /> 7093 ^jẹ́/*jẹ́$<br /> 6521 ^ń/*ń$<br /> 6085 ^ati/*ati$<br /> 5680 ^rẹ̀/*rẹ̀$<br /> 5556 ^sí/*sí$<br /> 5458 ^ọdún/*ọdún$<br /> 5237 ^to/*to$<br /> 5182 ^wọ́n/*wọ́n$<br /> 4846 ^èdè/*èdè$<br /> 4768 ^ṣe/*ṣe$<br /> 4717 ^the/*the$<br /> 4697 ^fún/*fún$<br /> 4513 ^of/*of$<br /> coverage: 287237 / 1283498 (~0.22379232379014225188)<br /> remaining unknown forms: 996261<br /> <br /> === The Bible ===<br /> TOP UNKNOWN WORDS:<br /> 9572 ^si/*si$<br /> 8152 ^ti/*ti$<br /> 3724 ^awọn/*awọn$<br /> 3530 ^ni/*ni$<br /> 3405 ^fun/*fun$<br /> 3204 ^li/*li$<br /> 3051 ^ki/*ki$<br /> 2841 ^ati/*ati$<br /> 2534 ^rẹ̀/*rẹ̀$<br /> 2412 ^nwọn/*nwọn$<br /> 2069 ^pe/*pe$<br /> 1965 ^nyin/*nyin$<br /> 1927 ^fi/*fi$<br /> 1872 ^bi/*bi$<br /> 1649 ^ninu/*ninu$<br /> 1648 ^ba/*ba$<br /> 1588 ^kò/*kò$<br /> 1506 ^ṣe/*ṣe$<br /> 1379 ^Ọlọrun/*Ọlọrun$<br /> 1278 ^lati/*lati$<br /> coverage: 53863 / 233959 (~0.23022409909428575092)<br /> <br /> remaining unknown forms: 180096<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14692 2021-05-20T20:53:02Z

<p>Cayoh1: /* Evaluation */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools and the lack of a standard orthography for the language. Yoruba is a tonal language and has many characters in the vocabulary are accented and can be written differently depending on which region you learned the language in. This has led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|thumb| Vowels Used in Yoruba]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> To evaluate my transducer, I tested coverage over two large corpuses in Yoruba; Wikipedia and the Bible.<br /> <br /> === Wikipedia ===<br /> <br /> TOP UNKNOWN WORDS:<br /> 26244 ^ni/*ni$<br /> 18828 ^tí/*tí$<br /> 16783 ^ti/*ti$<br /> 16252 ^ní/*ní$<br /> 9895 ^àwọn/*àwọn$<br /> 7621 ^àti/*àti$<br /> 7503 ^je/*je$<br /> 7093 ^jẹ́/*jẹ́$<br /> 6521 ^ń/*ń$<br /> 6085 ^ati/*ati$<br /> 5680 ^rẹ̀/*rẹ̀$<br /> 5556 ^sí/*sí$<br /> 5458 ^ọdún/*ọdún$<br /> 5237 ^to/*to$<br /> 5182 ^wọ́n/*wọ́n$<br /> 4846 ^èdè/*èdè$<br /> 4768 ^ṣe/*ṣe$<br /> 4717 ^the/*the$<br /> 4697 ^fún/*fún$<br /> 4513 ^of/*of$<br /> coverage: 287237 / 1283498 (~0.22379232379014225188)<br /> remaining unknown forms: 996261<br /> <br /> === The Bible ===<br /> TOP UNKNOWN WORDS:<br /> 9572 ^si/*si$<br /> 8152 ^ti/*ti$<br /> 3724 ^awọn/*awọn$<br /> 3530 ^ni/*ni$<br /> 3405 ^fun/*fun$<br /> 3204 ^li/*li$<br /> 3051 ^ki/*ki$<br /> 2841 ^ati/*ati$<br /> 2534 ^rẹ̀/*rẹ̀$<br /> 2412 ^nwọn/*nwọn$<br /> 2069 ^pe/*pe$<br /> 1965 ^nyin/*nyin$<br /> 1927 ^fi/*fi$<br /> 1872 ^bi/*bi$<br /> 1649 ^ninu/*ninu$<br /> 1648 ^ba/*ba$<br /> 1588 ^kò/*kò$<br /> 1506 ^ṣe/*ṣe$<br /> 1379 ^Ọlọrun/*Ọlọrun$<br /> 1278 ^lati/*lati$<br /> coverage: 53863 / 233959 (~0.23022409909428575092), &#039;&#039;&#039;23%&#039;&#039;&#039;<br /> remaining unknown forms: 180096<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14691 2021-05-20T20:52:30Z

<p>Cayoh1: /* Evaluation */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools and the lack of a standard orthography for the language. Yoruba is a tonal language and has many characters in the vocabulary are accented and can be written differently depending on which region you learned the language in. This has led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|thumb| Vowels Used in Yoruba]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> To evaluate my transducer, I tested coverage over two large corpuses in Yoruba; Wikipedia and the Bible.<br /> <br /> === Wikipedia ===<br /> <br /> TOP UNKNOWN WORDS:<br /> 26244 ^ni/*ni$<br /> 18828 ^tí/*tí$<br /> 16783 ^ti/*ti$<br /> 16252 ^ní/*ní$<br /> 9895 ^àwọn/*àwọn$<br /> 7621 ^àti/*àti$<br /> 7503 ^je/*je$<br /> 7093 ^jẹ́/*jẹ́$<br /> 6521 ^ń/*ń$<br /> 6085 ^ati/*ati$<br /> 5680 ^rẹ̀/*rẹ̀$<br /> 5556 ^sí/*sí$<br /> 5458 ^ọdún/*ọdún$<br /> 5237 ^to/*to$<br /> 5182 ^wọ́n/*wọ́n$<br /> 4846 ^èdè/*èdè$<br /> 4768 ^ṣe/*ṣe$<br /> 4717 ^the/*the$<br /> 4697 ^fún/*fún$<br /> 4513 ^of/*of$<br /> coverage: 287237 / 1283498 (~0.22379232379014225188)<br /> remaining unknown forms: 996261<br /> <br /> === The Bible ===<br /> TOP UNKNOWN WORDS:<br /> 9572 ^si/*si$<br /> 8152 ^ti/*ti$<br /> 3724 ^awọn/*awọn$<br /> 3530 ^ni/*ni$<br /> 3405 ^fun/*fun$<br /> 3204 ^li/*li$<br /> 3051 ^ki/*ki$<br /> 2841 ^ati/*ati$<br /> 2534 ^rẹ̀/*rẹ̀$<br /> 2412 ^nwọn/*nwọn$<br /> 2069 ^pe/*pe$<br /> 1965 ^nyin/*nyin$<br /> 1927 ^fi/*fi$<br /> 1872 ^bi/*bi$<br /> 1649 ^ninu/*ninu$<br /> 1648 ^ba/*ba$<br /> 1588 ^kò/*kò$<br /> 1506 ^ṣe/*ṣe$<br /> 1379 ^Ọlọrun/*Ọlọrun$<br /> 1278 ^lati/*lati$<br /> coverage: 53863 / 233959 (~0.23022409909428575092)<br /> remaining unknown forms: 180096<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14596 2021-05-18T23:28:05Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools and the lack of a standard orthography for the language. Yoruba is a tonal language and has many characters in the vocabulary are accented and can be written differently depending on which region you learned the language in. This has led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|thumb| Vowels Used in Yoruba]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> If you improve or make a transducer, you should test coverage over a large corpus and precision and recall against hand-annotated randomly selected forms;<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14595 2021-05-18T23:07:35Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|thumb| Vowels Used in Yoruba]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> If you improve or make a transducer, you should test coverage over a large corpus and precision and recall against hand-annotated randomly selected forms;<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14594 2021-05-18T22:53:44Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.3]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> If you improve or make a transducer, you should test coverage over a large corpus and precision and recall against hand-annotated randomly selected forms;<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14593 2021-05-18T22:53:27Z

<p>Cayoh1: /* Background */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still an under-resourced language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> If you improve or make a transducer, you should test coverage over a large corpus and precision and recall against hand-annotated randomly selected forms;<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=Category:Yoruba&diff=14592 2021-05-18T22:45:06Z

<p>Cayoh1: Created blank page</p> <hr /> <div></div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14591 2021-05-18T22:44:49Z

<p>Cayoh1: </p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> If you improve or make a transducer, you should test coverage over a large corpus and precision and recall against hand-annotated randomly selected forms;<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]][[Category:Yoruba]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14590 2021-05-18T22:44:32Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; there are different ways to say a number of things depending on the recipient.<br /> <br /> == Evaluation ==<br /> If you improve or make a transducer, you should test coverage over a large corpus and precision and recall against hand-annotated randomly selected forms;<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14589 2021-05-18T22:41:05Z

<p>Cayoh1: /* Evaluation */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; here are different ways to say things depending on the recipient.<br /> <br /> == Evaluation ==<br /> If you improve or make a transducer, you should test coverage over a large corpus and precision and recall against hand-annotated randomly selected forms;<br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14588 2021-05-18T22:40:39Z

<p>Cayoh1: /* Outline */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> * I used scraped text from Wikipedia and the Bible to evaluate my preliminary transducer on.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; here are different ways to say things depending on the recipient.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14587 2021-05-18T22:40:04Z

<p>Cayoh1: /* Moving Forward */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; here are different ways to say things depending on the recipient.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> I think that with further implementation, this resource would be very useful for the Yoruba Speaking community in Nigeria and the Yoruba diaspora community all over the world. I know that my peers who have also grown up with the language, but are not aware of its grammatical intricacies would benefit from this transducer to further learn about their native language. I think any addition to the computational tools for Yoruba will be positive as it is low resource compared to other languages with a similar number of speakers.<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14586 2021-05-18T22:36:50Z

<p>Cayoh1: /* Outline */</p> <hr /> <div>== Outline ==<br /> I have begun to create a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; here are different ways to say things depending on the recipient.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14585 2021-05-18T22:36:27Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> Also Yoruba doesn&#039;t have gendered or plural forms of nouns or adjectives, you express gender in some cases by adding another word, for example: &lt;code&gt;older sister&lt;/code&gt; in Yoruba would be &lt;code&gt;ẹ̀gbọ́n obìnrin&lt;/code&gt; with the first word meaning older sibling and the second word signifying female. Similar to Romance languages like French and Spanish, Yoruba also distinguishes verbs and interjections by familiarity; here are different ways to say things depending on the recipient.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14584 2021-05-18T22:33:01Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=0.5]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14583 2021-05-18T22:32:52Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|upright=1.0]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14582 2021-05-18T22:32:17Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|width:100 px]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14581 2021-05-18T22:31:40Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|width:300px]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14580 2021-05-18T22:31:31Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png|width:600px]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14579 2021-05-18T22:30:25Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png?maxwidth=600]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14578 2021-05-18T22:30:15Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png]?maxwidth=600] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14577 2021-05-18T22:29:29Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.png]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14576 2021-05-18T22:29:23Z

<p>Cayoh1: /* Issues */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> <br /> [[File:Vowels.ong]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=File:Vowels.png&diff=14575 2021-05-18T22:28:54Z

<p>Cayoh1: </p> <hr /> <div></div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14574 2021-05-18T22:28:35Z

<p>Cayoh1: /* Solution */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> === Background ===<br /> Essentially, even though there are up to 55 million speakers of Yoruba from Southwestern Nigeria, it is still a relatively low resource language. It does have limited Google Translate functionality and some documentation, but they could use a lot of improvement.<br /> <br /> === Approach ===<br /> With my knowledge of the language, growing up in a Yoruba speaking household and my knowledge of morphological analysis, I aimed to create a viable apertium transducer for the language that reflects how current speakers of the language use it. I have been checking with my family members to ensure my implementation is adequate.<br /> <br /> === Issues ===<br /> Some issues I&#039;ve run into are implementing correctly the Yoruba characters and structure with apertium tools. Yoruba is a tonal language and has many characters in the vocabulary are accented. This led to some difficulty in the beginning of characters not being represented correctly. <br /> [[File:Example.jpg]] <br /> <br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14573 2021-05-18T22:21:44Z

<p>Cayoh1: /* Outline */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I started writing rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14571 2021-05-18T21:49:32Z

<p>Cayoh1: /* Outline */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> * I added noun, verb, pronoun, adjectives, and interjections to the &lt;code&gt;lexd&lt;/code&gt; file.<br /> * In my grammar documentation, I created &lt;code&gt;morphTests&lt;/code&gt; to test morphological analysis.<br /> * I added preliminary rules in the &lt;code&gt;twol&lt;/code&gt; file.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14570 2021-05-18T21:46:49Z

<p>Cayoh1: /* Outline */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039; transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14569 2021-05-18T21:46:42Z

<p>Cayoh1: /* Outline */</p> <hr /> <div>== Outline ==<br /> I have created a &#039;&#039;&#039;very preliminary, basic&#039;&#039;&#039;transducer for Yoruba, my native Nigerian Language. I have used what we&#039;ve learned in class to build morphological analysis capabilities for my transducer.<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14568 2021-05-18T21:40:29Z

<p>Cayoh1: /* Code */</p> <hr /> <div>== Outline ==<br /> <br /> == Code/ Resources ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14567 2021-05-18T21:40:18Z

<p>Cayoh1: /* Code */</p> <hr /> <div>== Outline ==<br /> <br /> == Code ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> [https://wikis.swarthmore.edu/ling073/User:Cayoh1/Final_project/Grammar_Documentation Grammar Documentation]<br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project/Grammar_Documentation&diff=14566 2021-05-18T21:08:53Z

<p>Cayoh1: /* Nouns */</p> <hr /> <div><br /> == Nouns ==<br /> * {{morphTest|kan{{tag|n}}|kan}}<br /> * {{morphTest|ẹja{{tag|n}}|ẹja}}<br /> * {{morphTest|òpòló{{tag|n}}|òpòló}} <br /> * {{morphTest|àbúrò{{tag|n}}{{tag|f}}|àbúrò obìnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|f}}|ẹ̀gbọ́n obìnrin}}<br /> * {{morphTest|àbúrò{{tag|n}}{{tag|m}}|àbúrò arákùnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|m}}|ẹ̀gbọ́n arákùnrin}} <br /> * {{morphTest|ẹran{{tag|n}}|ẹran}} <br /> * {{morphTest|orúkọ{{tag|n}}|orúkọ}}<br /> * {{morphTest|adìyẹ{{tag|n}}|adìyẹ}}<br /> <br /> == Adjectives ==<br /> * {{morphTest|púpọ̀{{tag|adj}}|púpọ̀}} <br /> * {{morphTest|tóbi{{tag|adj}}|tóbi}} <br /> * {{morphTest|kan{{tag|adj}}{{tag|pl}}|kan}}<br /> * {{morphTest|méjì{{tag|adj}}{{tag|pl}}|méjì}} <br /> * {{morphTest|mẹta{{tag|adj}}{{tag|pl}}|mẹta}} <br /> * {{morphTest|mẹrin{{tag|adj}}{{tag|pl}}|mẹrin}}<br /> * {{morphTest|márùn{{tag|adj}}{{tag|pl}}|márùn}}</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project/Grammar_Documentation&diff=14565 2021-05-18T21:05:13Z

<p>Cayoh1: /* Adjectives */</p> <hr /> <div><br /> == Nouns ==<br /> * {{morphTest|kan{{tag|n}}|kan}}<br /> * {{morphTest|ẹja{{tag|n}}|ẹja}}<br /> * {{morphTest|òpòló{{tag|n}}|òpòló}} <br /> * {{morphTest|àbúrò{{tag|n}}{{tag|f}}|àbúrò obìnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|f}}|ẹ̀gbọ́n obìnrin}}<br /> * {{morphTest|àbúrò{{tag|n}}{{tag|m}}|àbúrò arákùnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|m}}|ẹ̀gbọ́n arákùnrin}} <br /> * {{morphTest|ẹran{{tag|n}}|ẹran}} <br /> * {{morphTest|orúkọ{{tag|n}}|orúkọ}}<br /> <br /> == Adjectives ==<br /> * {{morphTest|púpọ̀{{tag|adj}}|púpọ̀}} <br /> * {{morphTest|tóbi{{tag|adj}}|tóbi}} <br /> * {{morphTest|kan{{tag|adj}}{{tag|pl}}|kan}}<br /> * {{morphTest|méjì{{tag|adj}}{{tag|pl}}|méjì}} <br /> * {{morphTest|mẹta{{tag|adj}}{{tag|pl}}|mẹta}} <br /> * {{morphTest|mẹrin{{tag|adj}}{{tag|pl}}|mẹrin}}<br /> * {{morphTest|márùn{{tag|adj}}{{tag|pl}}|márùn}}</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project/Grammar_Documentation&diff=14564 2021-05-18T20:53:38Z

<p>Cayoh1: /* Adjectives */</p> <hr /> <div><br /> == Nouns ==<br /> * {{morphTest|kan{{tag|n}}|kan}}<br /> * {{morphTest|ẹja{{tag|n}}|ẹja}}<br /> * {{morphTest|òpòló{{tag|n}}|òpòló}} <br /> * {{morphTest|àbúrò{{tag|n}}{{tag|f}}|àbúrò obìnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|f}}|ẹ̀gbọ́n obìnrin}}<br /> * {{morphTest|àbúrò{{tag|n}}{{tag|m}}|àbúrò arákùnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|m}}|ẹ̀gbọ́n arákùnrin}} <br /> * {{morphTest|ẹran{{tag|n}}|ẹran}} <br /> * {{morphTest|orúkọ{{tag|n}}|orúkọ}}<br /> <br /> == Adjectives ==<br /> * {{morphTest|púpọ̀{{tag|adj}}|púpọ̀}} <br /> * {{morphTest|tóbi{{tag|adj}}|tóbi}} <br /> * {{morphTest|kan{{tag|adj}}{{tag|pl}}|kan}}<br /> * {{morphTest|méjì{{tag|adj}}{{tag|pl}}|méjì}} <br /> * {{morphTest|mẹta{{tag|adj}}{{tag|pl}}|mẹta}} <br /> * {{morphTest|mẹta{{tag|adj}}{{tag|pl}}|mẹta}}<br /> * {{morphTest|márùn{{tag|adj}}{{tag|pl}}|márùn}}</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project/Grammar_Documentation&diff=14563 2021-05-18T20:40:11Z

<p>Cayoh1: /* Adjectives */</p> <hr /> <div><br /> == Nouns ==<br /> * {{morphTest|kan{{tag|n}}|kan}}<br /> * {{morphTest|ẹja{{tag|n}}|ẹja}}<br /> * {{morphTest|òpòló{{tag|n}}|òpòló}} <br /> * {{morphTest|àbúrò{{tag|n}}{{tag|f}}|àbúrò obìnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|f}}|ẹ̀gbọ́n obìnrin}}<br /> * {{morphTest|àbúrò{{tag|n}}{{tag|m}}|àbúrò arákùnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|m}}|ẹ̀gbọ́n arákùnrin}} <br /> * {{morphTest|ẹran{{tag|n}}|ẹran}} <br /> * {{morphTest|orúkọ{{tag|n}}|orúkọ}}<br /> <br /> == Adjectives ==<br /> * {{morphTest|púpọ̀{{tag|adj}}|púpọ̀}} <br /> * {{morphTest|tóbi{{tag|adj}}|tóbi}}</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project/Grammar_Documentation&diff=14562 2021-05-18T20:36:44Z

<p>Cayoh1: /* Nouns */</p> <hr /> <div><br /> == Nouns ==<br /> * {{morphTest|kan{{tag|n}}|kan}}<br /> * {{morphTest|ẹja{{tag|n}}|ẹja}}<br /> * {{morphTest|òpòló{{tag|n}}|òpòló}} <br /> * {{morphTest|àbúrò{{tag|n}}{{tag|f}}|àbúrò obìnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|f}}|ẹ̀gbọ́n obìnrin}}<br /> * {{morphTest|àbúrò{{tag|n}}{{tag|m}}|àbúrò arákùnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|m}}|ẹ̀gbọ́n arákùnrin}} <br /> * {{morphTest|ẹran{{tag|n}}|ẹran}} <br /> * {{morphTest|orúkọ{{tag|n}}|orúkọ}}<br /> <br /> == Adjectives ==<br /> * {{morphTest|púpọ̀{{tag|adj}}|púpọ̀}}</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project/Grammar_Documentation&diff=14561 2021-05-18T20:32:18Z

<p>Cayoh1: /* Yoruba Alternations */</p> <hr /> <div><br /> == Nouns ==<br /> * {{morphTest|kan{{tag|n}}|kan}}<br /> * {{morphTest|ẹja{{tag|n}}|ẹja}}<br /> * {{morphTest|òpòló{{tag|n}}|òpòló}} <br /> * {{morphTest|àbúrò{{tag|n}}{{tag|f}}|àbúrò obìnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|f}}|ẹ̀gbọ́n obìnrin}}<br /> * {{morphTest|àbúrò{{tag|n}}{{tag|m}}|àbúrò arákùnrin}} <br /> * {{morphTest|ẹ̀gbọ́n{{tag|n}}{{tag|m}}|ẹ̀gbọ́n arákùnrin}} <br /> * {{morphTest|ẹran{{tag|n}}|ẹran}}<br /> <br /> == Adjectives ==<br /> * {{morphTest|púpọ̀{{tag|adj}}|púpọ̀}}</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project/Grammar_Documentation&diff=14560 2021-05-18T20:14:47Z

<p>Cayoh1: /* Alternation 1: feminine noun */</p> <hr /> <div><br /> == Yoruba Alternations ==<br /> === Nouns ===<br /> * {{morphTest|ti{{tag|n}}{{tag|f}}|tinga}}<br /> * {{morphTest|manta{{tag|n}}{{tag|f}}|mantanga}}</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project/Grammar_Documentation&diff=14559 2021-05-18T20:11:45Z

<p>Cayoh1: Created page with &quot; == Yoruba Alternations == === Alternation 1: feminine noun === * {{morphTest|ti{{tag|n}}{{tag|f}}|tinga}} * {{morphTest|manta{{tag|n}}{{tag|f}}|mantanga}}&quot;</p> <hr /> <div><br /> == Yoruba Alternations ==<br /> === Alternation 1: feminine noun ===<br /> * {{morphTest|ti{{tag|n}}{{tag|f}}|tinga}}<br /> * {{morphTest|manta{{tag|n}}{{tag|f}}|mantanga}}</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14558 2021-05-18T20:09:43Z

<p>Cayoh1: /* Code */</p> <hr /> <div>== Outline ==<br /> <br /> == Code ==<br /> [https://github.swarthmore.edu/Ling073-sp21/ling73-yor Github]<br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14437 2021-05-15T23:35:38Z

<p>Cayoh1: /* Moving Forward */</p> <hr /> <div>== Outline ==<br /> <br /> == Code ==<br /> <br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> Your thoughts on who might benefit from your project and in what way. E.g., might a language community be able to find a use for what you&#039;re doing, or maybe [computational] linguists working on a language or issue? Remember that Bird (2020) advocates for evaluating in this way—it just might not be possible to do so within the context of this class.<br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14436 2021-05-15T23:35:26Z

<p>Cayoh1: /* Headline text */</p> <hr /> <div>== Outline ==<br /> <br /> == Code ==<br /> <br /> <br /> == Solution ==<br /> How you&#039;re approaching the solution to the overall problem, including how you&#039;re implementing the solution. You can talk here about smaller individual issues that have arisen as well.<br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> <br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14374 2021-05-12T15:59:27Z

<p>Cayoh1: </p> <hr /> <div>== Outline ==<br /> <br /> == Code ==<br /> <br /> <br /> == Headline text ==<br /> <br /> <br /> == Evaluation ==<br /> <br /> <br /> == Moving Forward ==<br /> <br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Cayoh1/Final_project&diff=14373 2021-05-12T15:58:10Z

<p>Cayoh1: </p> <hr /> <div>== Outline ==<br /> <br /> == Code ==<br /> <br /> <br /> == Headline text ==<br /> <br /> <br /> == Evaluation ==<br /> <br /> <br /> <br /> [[Category:sp21_FinalProjects]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=Tiwi_and_English/Structural_transfer&diff=14311 2021-05-07T19:42:59Z

<p>Cayoh1: /* Examples */</p> <hr /> <div><br /> == Pre-Evaluation ==<br /> ===Statistics about input files===<br /> Number of words in reference: 41<br /> <br /> Number of words in test: 28<br /> <br /> Number of unknown words (marked with a star) in test: 13<br /> <br /> Percentage of unknown words: 14.63%<br /> <br /> ===Results when removing unknown-word marks (stars)===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Results when unknown-word marks (stars) are not removed===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Statistics about the translation of unknown words===<br /> Number of unknown words which were free rides: 0<br /> <br /> Percentage of unknown words that were free rides: 0%<br /> <br /> == Examples ==<br /> <br /> === Gendered Nouns and Adjectives ===<br /> ==== Tiw-Eng ==== <br /> (tiw) ngarra kijinga → (eng) he is small<br /> <br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|ngarra{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|m}}{{tag|sg}} kiji {{tag|adj}}{{tag|f}}| prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|m}}{{tag|sg}} be {{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} small {{tag|adj}}{{tag|sint}} }}<br /> <br /> ==== Biltrans ==== <br /> ^ngarra&lt;prn&gt;&lt;m&gt;&lt;p3&gt;&lt;sg&gt;/he&lt;prn&gt;&lt;m&gt;&lt;p3&gt;&lt;sg&gt;$ ^kiji&lt;adj&gt;&lt;f&gt;/small&lt;adj&gt;&lt;sint&gt;&lt;f&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^he&lt;prn&gt;&lt;p3&gt;&lt;m&gt;&lt;sg&gt;$ ^be&lt;vbser&gt;&lt;pres&gt;&lt;p3&gt;&lt;sg&gt;$ ^small&lt;adj&gt;&lt;sint&gt;$^.&lt;sent&gt;$<br /> <br /> === Insert &quot;Be&quot; Verbs ===<br /> ==== Tiw-Eng ==== <br /> (tiw) kamini naki? → (eng) what is this?<br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|kami{{tag|prn}}{{tag|itg}}{{tag|m}} naki{{tag|prn}}{{tag|dem}}{{tag|sg}} | what {{tag|prn}}{{tag|itg}}{{tag|mf}}{{tag|sp}} be {{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} this{{tag|prn}}{{tag|dem}}{{tag|mf}}{{tag|sg}} }}<br /> <br /> ==== Biltrans ==== <br /> ^kami&lt;prn&gt;&lt;itg&gt;&lt;m&gt;/what&lt;prn&gt;&lt;itg&gt;&lt;m&gt;/which&lt;prn&gt;&lt;itg&gt;&lt;m&gt;$ ^naki&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;/this&gt;&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^what&lt;prn&gt;&lt;itg&gt;&lt;m&gt;$ ^be&lt;vbser&gt;&lt;pres&gt;&lt;p3&gt;&lt;sg&gt;$ ^this&gt;&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;$^.&lt;sent&gt;$<br /> <br /> === Word to Word Phrase ===<br /> ==== Tiw-Eng ==== <br /> {{transferTest|tiw|eng|jupijupi awi kiyija mirrawu | soup and a little bit of tobacco}} <br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|jupijupi{{tag|n}} awi {{tag|cnjcoo}} kiyija{{tag|prn}}{{tag|qnt}} mirrawu {{tag|n}} | soup{{tag|n}}{{tag|sg}} and {{tag|cnjcoo}} a little bit {{tag|adv}} of {{tag|pr}} tobacco {{tag|n}}{{tag|sg}} }}<br /> ==== Biltrans ==== <br /> ^jupijupi&lt;n&gt;/soup&lt;n&gt;$ ^awi&lt;cnjcoo&gt;/and&lt;cnjcoo&gt;$ ^kiyija&lt;prn&gt;&lt;qnt&gt;/a little bit&lt;adv&gt;$ ^mirrawu&lt;n&gt;/tobacco&lt;n&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^soup&lt;n&gt;&lt;sg&gt;$ ^and&lt;cnjcoo&gt;$ ^a little bit&lt;adv&gt;$ ^of&lt;pr&gt;$ ^tobacco&lt;n&gt;&lt;sg&gt;$^.&lt;sent&gt;$<br /> <br /> == Post Evaluation ==<br /> ===Statistics about input files===<br /> Number of words in reference: 41<br /> <br /> Number of words in test: 28<br /> <br /> Number of unknown words (marked with a star) in test: 13<br /> <br /> Percentage of unknown words: 46.43%<br /> <br /> ===Results when removing unknown-word marks (stars)===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Results when unknown-word marks (stars) are not removed===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Statistics about the translation of unknown words===<br /> Number of unknown words which were free rides: 0<br /> <br /> Percentage of unknown words that were free rides: 0%<br /> <br /> <br /> [[Category:Sp21_StructuralTransfer]] [[Category:Tiwi]] [[Category:English]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=Tiwi_and_English/Structural_transfer&diff=14310 2021-05-07T19:42:44Z

<p>Cayoh1: /* Eng-Tiw */</p> <hr /> <div><br /> == Pre-Evaluation ==<br /> ===Statistics about input files===<br /> Number of words in reference: 41<br /> <br /> Number of words in test: 28<br /> <br /> Number of unknown words (marked with a star) in test: 13<br /> <br /> Percentage of unknown words: 14.63%<br /> <br /> ===Results when removing unknown-word marks (stars)===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Results when unknown-word marks (stars) are not removed===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Statistics about the translation of unknown words===<br /> Number of unknown words which were free rides: 0<br /> <br /> Percentage of unknown words that were free rides: 0%<br /> <br /> == Examples ==<br /> <br /> === Gendered Nouns and Adjectives ===<br /> ==== Tiw-Eng ==== <br /> (tiw) ngarra kijinga → (eng) he is small<br /> <br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|ngarra{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|m}}{{tag|sg}} kiji {{tag|adj}}{{tag|f}}| prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|m}}{{tag|sg}} be {{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} small {{tag|adj}}{{tag|sint}} }}<br /> <br /> ==== Biltrans ==== <br /> ^ngarra&lt;prn&gt;&lt;m&gt;&lt;p3&gt;&lt;sg&gt;/he&lt;prn&gt;&lt;m&gt;&lt;p3&gt;&lt;sg&gt;$ ^kiji&lt;adj&gt;&lt;f&gt;/small&lt;adj&gt;&lt;sint&gt;&lt;f&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^he&lt;prn&gt;&lt;p3&gt;&lt;m&gt;&lt;sg&gt;$ ^be&lt;vbser&gt;&lt;pres&gt;&lt;p3&gt;&lt;sg&gt;$ ^small&lt;adj&gt;&lt;sint&gt;$^.&lt;sent&gt;$<br /> <br /> === Insert &quot;Be&quot; Verbs ===<br /> ==== Eng-Tiw ==== <br /> (tiw) kamini naki? → (eng) what is this?<br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|kami{{tag|prn}}{{tag|itg}}{{tag|m}} naki{{tag|prn}}{{tag|dem}}{{tag|sg}} | what {{tag|prn}}{{tag|itg}}{{tag|mf}}{{tag|sp}} be {{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} this{{tag|prn}}{{tag|dem}}{{tag|mf}}{{tag|sg}} }}<br /> <br /> ==== Biltrans ==== <br /> ^kami&lt;prn&gt;&lt;itg&gt;&lt;m&gt;/what&lt;prn&gt;&lt;itg&gt;&lt;m&gt;/which&lt;prn&gt;&lt;itg&gt;&lt;m&gt;$ ^naki&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;/this&gt;&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^what&lt;prn&gt;&lt;itg&gt;&lt;m&gt;$ ^be&lt;vbser&gt;&lt;pres&gt;&lt;p3&gt;&lt;sg&gt;$ ^this&gt;&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;$^.&lt;sent&gt;$<br /> <br /> === Word to Word Phrase ===<br /> ==== Eng-Tiw ==== <br /> {{transferTest|tiw|eng|jupijupi awi kiyija mirrawu | soup and a little bit of tobacco}} <br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|jupijupi{{tag|n}} awi {{tag|cnjcoo}} kiyija{{tag|prn}}{{tag|qnt}} mirrawu {{tag|n}} | soup{{tag|n}}{{tag|sg}} and {{tag|cnjcoo}} a little bit {{tag|adv}} of {{tag|pr}} tobacco {{tag|n}}{{tag|sg}} }}<br /> ==== Biltrans ==== <br /> ^jupijupi&lt;n&gt;/soup&lt;n&gt;$ ^awi&lt;cnjcoo&gt;/and&lt;cnjcoo&gt;$ ^kiyija&lt;prn&gt;&lt;qnt&gt;/a little bit&lt;adv&gt;$ ^mirrawu&lt;n&gt;/tobacco&lt;n&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^soup&lt;n&gt;&lt;sg&gt;$ ^and&lt;cnjcoo&gt;$ ^a little bit&lt;adv&gt;$ ^of&lt;pr&gt;$ ^tobacco&lt;n&gt;&lt;sg&gt;$^.&lt;sent&gt;$<br /> <br /> == Post Evaluation ==<br /> ===Statistics about input files===<br /> Number of words in reference: 41<br /> <br /> Number of words in test: 28<br /> <br /> Number of unknown words (marked with a star) in test: 13<br /> <br /> Percentage of unknown words: 46.43%<br /> <br /> ===Results when removing unknown-word marks (stars)===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Results when unknown-word marks (stars) are not removed===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Statistics about the translation of unknown words===<br /> Number of unknown words which were free rides: 0<br /> <br /> Percentage of unknown words that were free rides: 0%<br /> <br /> <br /> [[Category:Sp21_StructuralTransfer]] [[Category:Tiwi]] [[Category:English]]</div>

Cayoh1 http://wikis.swarthmore.edu/ling073/index.php?title=Tiwi_and_English/Structural_transfer&diff=14309 2021-05-07T19:35:24Z

<p>Cayoh1: /* Tagger */</p> <hr /> <div><br /> == Pre-Evaluation ==<br /> ===Statistics about input files===<br /> Number of words in reference: 41<br /> <br /> Number of words in test: 28<br /> <br /> Number of unknown words (marked with a star) in test: 13<br /> <br /> Percentage of unknown words: 14.63%<br /> <br /> ===Results when removing unknown-word marks (stars)===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Results when unknown-word marks (stars) are not removed===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Statistics about the translation of unknown words===<br /> Number of unknown words which were free rides: 0<br /> <br /> Percentage of unknown words that were free rides: 0%<br /> <br /> == Examples ==<br /> <br /> === Gendered Nouns and Adjectives ===<br /> ==== Eng-Tiw ==== <br /> (tiw) ngarra kijinga → (eng) he is small<br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|ngarra{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|m}}{{tag|sg}} kiji {{tag|adj}}{{tag|f}}| prpers{{tag|prn}}{{tag|subj}}{{tag|p3}}{{tag|m}}{{tag|sg}} be {{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} small {{tag|adj}}{{tag|sint}} }}<br /> <br /> ==== Biltrans ==== <br /> ^ngarra&lt;prn&gt;&lt;m&gt;&lt;p3&gt;&lt;sg&gt;/he&lt;prn&gt;&lt;m&gt;&lt;p3&gt;&lt;sg&gt;$ ^kiji&lt;adj&gt;&lt;f&gt;/small&lt;adj&gt;&lt;sint&gt;&lt;f&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^he&lt;prn&gt;&lt;p3&gt;&lt;m&gt;&lt;sg&gt;$ ^be&lt;vbser&gt;&lt;pres&gt;&lt;p3&gt;&lt;sg&gt;$ ^small&lt;adj&gt;&lt;sint&gt;$^.&lt;sent&gt;$<br /> <br /> === Insert &quot;Be&quot; Verbs ===<br /> ==== Eng-Tiw ==== <br /> (tiw) kamini naki? → (eng) what is this?<br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|kami{{tag|prn}}{{tag|itg}}{{tag|m}} naki{{tag|prn}}{{tag|dem}}{{tag|sg}} | what {{tag|prn}}{{tag|itg}}{{tag|mf}}{{tag|sp}} be {{tag|vbser}}{{tag|pres}}{{tag|p3}}{{tag|sg}} this{{tag|prn}}{{tag|dem}}{{tag|mf}}{{tag|sg}} }}<br /> <br /> ==== Biltrans ==== <br /> ^kami&lt;prn&gt;&lt;itg&gt;&lt;m&gt;/what&lt;prn&gt;&lt;itg&gt;&lt;m&gt;/which&lt;prn&gt;&lt;itg&gt;&lt;m&gt;$ ^naki&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;/this&gt;&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^what&lt;prn&gt;&lt;itg&gt;&lt;m&gt;$ ^be&lt;vbser&gt;&lt;pres&gt;&lt;p3&gt;&lt;sg&gt;$ ^this&gt;&lt;prn&gt;&lt;dem&gt;&lt;sg&gt;$^.&lt;sent&gt;$<br /> <br /> === Word to Word Phrase ===<br /> ==== Eng-Tiw ==== <br /> {{transferTest|tiw|eng|jupijupi awi kiyija mirrawu | soup and a little bit of tobacco}} <br /> ==== Tagger ==== <br /> {{transferMorphTest|tiw|eng|jupijupi{{tag|n}} awi {{tag|cnjcoo}} kiyija{{tag|prn}}{{tag|qnt}} mirrawu {{tag|n}} | soup{{tag|n}}{{tag|sg}} and {{tag|cnjcoo}} a little bit {{tag|adv}} of {{tag|pr}} tobacco {{tag|n}}{{tag|sg}} }}<br /> ==== Biltrans ==== <br /> ^jupijupi&lt;n&gt;/soup&lt;n&gt;$ ^awi&lt;cnjcoo&gt;/and&lt;cnjcoo&gt;$ ^kiyija&lt;prn&gt;&lt;qnt&gt;/a little bit&lt;adv&gt;$ ^mirrawu&lt;n&gt;/tobacco&lt;n&gt;$^.&lt;sent&gt;/.&lt;sent&gt;$<br /> ==== Transfer ==== <br /> ^soup&lt;n&gt;&lt;sg&gt;$ ^and&lt;cnjcoo&gt;$ ^a little bit&lt;adv&gt;$ ^of&lt;pr&gt;$ ^tobacco&lt;n&gt;&lt;sg&gt;$^.&lt;sent&gt;$<br /> <br /> == Post Evaluation ==<br /> ===Statistics about input files===<br /> Number of words in reference: 41<br /> <br /> Number of words in test: 28<br /> <br /> Number of unknown words (marked with a star) in test: 13<br /> <br /> Percentage of unknown words: 46.43%<br /> <br /> ===Results when removing unknown-word marks (stars)===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Results when unknown-word marks (stars) are not removed===<br /> Edit distance: 36<br /> <br /> Word error rate (WER): 87.8%<br /> <br /> Number of position-independent correct words: 5<br /> <br /> Position-independent word error rate (PER): 87.8%<br /> <br /> ===Statistics about the translation of unknown words===<br /> Number of unknown words which were free rides: 0<br /> <br /> Percentage of unknown words that were free rides: 0%<br /> <br /> <br /> [[Category:Sp21_StructuralTransfer]] [[Category:Tiwi]] [[Category:English]]</div>

Cayoh1