@inproceedings{byamugisha-2022-noun,
title = "Noun Class Disambiguation in {R}unyankore and Related Languages",
author = "Byamugisha, Joan",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.383",
pages = "4350--4359",
abstract = "Bantu languages are spoken by communities in more than half of the countries on the African continent by an estimated third of a billion people. Despite this populous and the amount of high quality linguistic research done over the years, Bantu languages are still computationally under-resourced. The biggest limitation to the development of computational methods for processing Bantu language text is their complex grammatical structure, chiefly in the system of noun classes. We investigated the use of a combined syntactic and semantic method to disambiguate among singular nouns with the same class prefix but belonging to different noun classes. This combination uses the semantic generalizations of the types of nouns in each class to overcome the limitations of relying only on the prefixes they take. We used the nearest neighbors of a query word as semantic generalizations, and developed a tool to determine the noun class based on resources in Runyankore, a Bantu language indigenous to Uganda. We also investigated whether, with the same Runyankore resources, our method had utility in other Bantu languages, Luganda, indigenous to Uganda, and Kinyarwanda, indigenous to Rwanda. For all three languages, the combined approach resulted in an improvement in accuracy, as compared to using only the syntactic or the semantic approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="byamugisha-2022-noun">
<titleInfo>
<title>Noun Class Disambiguation in Runyankore and Related Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joan</namePart>
<namePart type="family">Byamugisha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bantu languages are spoken by communities in more than half of the countries on the African continent by an estimated third of a billion people. Despite this populous and the amount of high quality linguistic research done over the years, Bantu languages are still computationally under-resourced. The biggest limitation to the development of computational methods for processing Bantu language text is their complex grammatical structure, chiefly in the system of noun classes. We investigated the use of a combined syntactic and semantic method to disambiguate among singular nouns with the same class prefix but belonging to different noun classes. This combination uses the semantic generalizations of the types of nouns in each class to overcome the limitations of relying only on the prefixes they take. We used the nearest neighbors of a query word as semantic generalizations, and developed a tool to determine the noun class based on resources in Runyankore, a Bantu language indigenous to Uganda. We also investigated whether, with the same Runyankore resources, our method had utility in other Bantu languages, Luganda, indigenous to Uganda, and Kinyarwanda, indigenous to Rwanda. For all three languages, the combined approach resulted in an improvement in accuracy, as compared to using only the syntactic or the semantic approach.</abstract>
<identifier type="citekey">byamugisha-2022-noun</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.383</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4350</start>
<end>4359</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Noun Class Disambiguation in Runyankore and Related Languages
%A Byamugisha, Joan
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F byamugisha-2022-noun
%X Bantu languages are spoken by communities in more than half of the countries on the African continent by an estimated third of a billion people. Despite this populous and the amount of high quality linguistic research done over the years, Bantu languages are still computationally under-resourced. The biggest limitation to the development of computational methods for processing Bantu language text is their complex grammatical structure, chiefly in the system of noun classes. We investigated the use of a combined syntactic and semantic method to disambiguate among singular nouns with the same class prefix but belonging to different noun classes. This combination uses the semantic generalizations of the types of nouns in each class to overcome the limitations of relying only on the prefixes they take. We used the nearest neighbors of a query word as semantic generalizations, and developed a tool to determine the noun class based on resources in Runyankore, a Bantu language indigenous to Uganda. We also investigated whether, with the same Runyankore resources, our method had utility in other Bantu languages, Luganda, indigenous to Uganda, and Kinyarwanda, indigenous to Rwanda. For all three languages, the combined approach resulted in an improvement in accuracy, as compared to using only the syntactic or the semantic approach.
%U https://aclanthology.org/2022.coling-1.383
%P 4350-4359
Markdown (Informal)
[Noun Class Disambiguation in Runyankore and Related Languages](https://aclanthology.org/2022.coling-1.383) (Byamugisha, COLING 2022)
ACL