@inproceedings{sato-2024-disambiguating,
title = "Disambiguating Homographs and Homophones Simultaneously: A Regrouping Method for {J}apanese",
author = "Sato, Yo",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.442",
pages = "4935--4939",
abstract = "We present a method that re-groups surface forms into clusters representing synonyms, and help disambiguate homographs as well as homophone. The method is applied post-hoc to trained contextual word embeddings. It is beneficial to languages where both homographs and homophones abound, which compromise the efficiency of language model and causes the underestimation problem in evaluation. Taking Japanese as an example, we evaluate how accurate such disambiguation can be, and how much the underestimation can be mitigated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sato-2024-disambiguating">
<titleInfo>
<title>Disambiguating Homographs and Homophones Simultaneously: A Regrouping Method for Japanese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yo</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</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>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a method that re-groups surface forms into clusters representing synonyms, and help disambiguate homographs as well as homophone. The method is applied post-hoc to trained contextual word embeddings. It is beneficial to languages where both homographs and homophones abound, which compromise the efficiency of language model and causes the underestimation problem in evaluation. Taking Japanese as an example, we evaluate how accurate such disambiguation can be, and how much the underestimation can be mitigated.</abstract>
<identifier type="citekey">sato-2024-disambiguating</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.442</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4935</start>
<end>4939</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disambiguating Homographs and Homophones Simultaneously: A Regrouping Method for Japanese
%A Sato, Yo
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F sato-2024-disambiguating
%X We present a method that re-groups surface forms into clusters representing synonyms, and help disambiguate homographs as well as homophone. The method is applied post-hoc to trained contextual word embeddings. It is beneficial to languages where both homographs and homophones abound, which compromise the efficiency of language model and causes the underestimation problem in evaluation. Taking Japanese as an example, we evaluate how accurate such disambiguation can be, and how much the underestimation can be mitigated.
%U https://aclanthology.org/2024.lrec-main.442
%P 4935-4939
Markdown (Informal)
[Disambiguating Homographs and Homophones Simultaneously: A Regrouping Method for Japanese](https://aclanthology.org/2024.lrec-main.442) (Sato, LREC-COLING 2024)
ACL