@inproceedings{zheng-etal-2021-leveraging-word,
title = "Leveraging Word-Formation Knowledge for {C}hinese Word Sense Disambiguation",
author = "Zheng, Hua and
Li, Lei and
Dai, Damai and
Chen, Deli and
Liu, Tianyu and
Sun, Xu and
Liu, Yang",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.78",
doi = "10.18653/v1/2021.findings-emnlp.78",
pages = "918--923",
abstract = "In parataxis languages like Chinese, word meanings are constructed using specific word-formations, which can help to disambiguate word senses. However, such knowledge is rarely explored in previous word sense disambiguation (WSD) methods. In this paper, we propose to leverage word-formation knowledge to enhance Chinese WSD. We first construct a large-scale Chinese lexical sample WSD dataset with word-formations. Then, we propose a model FormBERT to explicitly incorporate word-formations into sense disambiguation. To further enhance generalizability, we design a word-formation predictor module in case word-formation annotations are unavailable. Experimental results show that our method brings substantial performance improvement over strong baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2021-leveraging-word">
<titleInfo>
<title>Leveraging Word-Formation Knowledge for Chinese Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damai</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deli</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Sun</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>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In parataxis languages like Chinese, word meanings are constructed using specific word-formations, which can help to disambiguate word senses. However, such knowledge is rarely explored in previous word sense disambiguation (WSD) methods. In this paper, we propose to leverage word-formation knowledge to enhance Chinese WSD. We first construct a large-scale Chinese lexical sample WSD dataset with word-formations. Then, we propose a model FormBERT to explicitly incorporate word-formations into sense disambiguation. To further enhance generalizability, we design a word-formation predictor module in case word-formation annotations are unavailable. Experimental results show that our method brings substantial performance improvement over strong baselines.</abstract>
<identifier type="citekey">zheng-etal-2021-leveraging-word</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.78</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.78</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>918</start>
<end>923</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Word-Formation Knowledge for Chinese Word Sense Disambiguation
%A Zheng, Hua
%A Li, Lei
%A Dai, Damai
%A Chen, Deli
%A Liu, Tianyu
%A Sun, Xu
%A Liu, Yang
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F zheng-etal-2021-leveraging-word
%X In parataxis languages like Chinese, word meanings are constructed using specific word-formations, which can help to disambiguate word senses. However, such knowledge is rarely explored in previous word sense disambiguation (WSD) methods. In this paper, we propose to leverage word-formation knowledge to enhance Chinese WSD. We first construct a large-scale Chinese lexical sample WSD dataset with word-formations. Then, we propose a model FormBERT to explicitly incorporate word-formations into sense disambiguation. To further enhance generalizability, we design a word-formation predictor module in case word-formation annotations are unavailable. Experimental results show that our method brings substantial performance improvement over strong baselines.
%R 10.18653/v1/2021.findings-emnlp.78
%U https://aclanthology.org/2021.findings-emnlp.78
%U https://doi.org/10.18653/v1/2021.findings-emnlp.78
%P 918-923
Markdown (Informal)
[Leveraging Word-Formation Knowledge for Chinese Word Sense Disambiguation](https://aclanthology.org/2021.findings-emnlp.78) (Zheng et al., Findings 2021)
ACL