@inproceedings{wang-etal-2024-disambiguate,
title = "Disambiguate Words like Composing Them: A Morphology-Informed Approach to Enhance {C}hinese Word Sense Disambiguation",
author = "Wang, Yue and
Liang, Qiliang and
Yin, Yaqi and
Wang, Hansi and
Liu, Yang",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.819",
doi = "10.18653/v1/2024.acl-long.819",
pages = "15354--15365",
abstract = "In parataxis languages like Chinese, word meanings are highly correlated with morphological knowledge, which can help to disambiguate word senses. However, in-depth exploration of morphological knowledge in previous word sense disambiguation (WSD) methods is still lacking due to the absence of publicly available resources. In this paper, we are motivated to enhance Chinese WSD with full morphological knowledge, including both word-formations and morphemes. We first construct the largest and releasable Chinese WSD resources, including the lexico-semantic inventories MorInv and WrdInv, a Chinese WSD dataset MiCLS, and an out-of-volcabulary (OOV) test set. Then, we propose a model, MorBERT, to fully leverage this morphology-informed knowledge for Chinese WSD and achieve a SOTA F1 of 92.18{\%} in the task. Finally, we demonstrated the model{'}s robustness in low-resource settings and generalizability to OOV senses. These resources and methods may bring new insights into and solutions for various downstream tasks in both computational and humanistic fields.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-disambiguate">
<titleInfo>
<title>Disambiguate Words like Composing Them: A Morphology-Informed Approach to Enhance Chinese Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiliang</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaqi</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In parataxis languages like Chinese, word meanings are highly correlated with morphological knowledge, which can help to disambiguate word senses. However, in-depth exploration of morphological knowledge in previous word sense disambiguation (WSD) methods is still lacking due to the absence of publicly available resources. In this paper, we are motivated to enhance Chinese WSD with full morphological knowledge, including both word-formations and morphemes. We first construct the largest and releasable Chinese WSD resources, including the lexico-semantic inventories MorInv and WrdInv, a Chinese WSD dataset MiCLS, and an out-of-volcabulary (OOV) test set. Then, we propose a model, MorBERT, to fully leverage this morphology-informed knowledge for Chinese WSD and achieve a SOTA F1 of 92.18% in the task. Finally, we demonstrated the model’s robustness in low-resource settings and generalizability to OOV senses. These resources and methods may bring new insights into and solutions for various downstream tasks in both computational and humanistic fields.</abstract>
<identifier type="citekey">wang-etal-2024-disambiguate</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.819</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.819</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>15354</start>
<end>15365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disambiguate Words like Composing Them: A Morphology-Informed Approach to Enhance Chinese Word Sense Disambiguation
%A Wang, Yue
%A Liang, Qiliang
%A Yin, Yaqi
%A Wang, Hansi
%A Liu, Yang
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-disambiguate
%X In parataxis languages like Chinese, word meanings are highly correlated with morphological knowledge, which can help to disambiguate word senses. However, in-depth exploration of morphological knowledge in previous word sense disambiguation (WSD) methods is still lacking due to the absence of publicly available resources. In this paper, we are motivated to enhance Chinese WSD with full morphological knowledge, including both word-formations and morphemes. We first construct the largest and releasable Chinese WSD resources, including the lexico-semantic inventories MorInv and WrdInv, a Chinese WSD dataset MiCLS, and an out-of-volcabulary (OOV) test set. Then, we propose a model, MorBERT, to fully leverage this morphology-informed knowledge for Chinese WSD and achieve a SOTA F1 of 92.18% in the task. Finally, we demonstrated the model’s robustness in low-resource settings and generalizability to OOV senses. These resources and methods may bring new insights into and solutions for various downstream tasks in both computational and humanistic fields.
%R 10.18653/v1/2024.acl-long.819
%U https://aclanthology.org/2024.acl-long.819
%U https://doi.org/10.18653/v1/2024.acl-long.819
%P 15354-15365
Markdown (Informal)
[Disambiguate Words like Composing Them: A Morphology-Informed Approach to Enhance Chinese Word Sense Disambiguation](https://aclanthology.org/2024.acl-long.819) (Wang et al., ACL 2024)
ACL