@inproceedings{hou-etal-2020-try,
title = "Try to Substitute: An Unsupervised {C}hinese Word Sense Disambiguation Method Based on {H}ow{N}et",
author = "Hou, Bairu and
Qi, Fanchao and
Zang, Yuan and
Zhang, Xurui and
Liu, Zhiyuan and
Sun, Maosong",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.155/",
doi = "10.18653/v1/2020.coling-main.155",
pages = "1752--1757",
abstract = "Word sense disambiguation (WSD) is a fundamental natural language processing task. Unsupervised knowledge-based WSD only relies on a lexical knowledge base as the sense inventory and has wider practical use than supervised WSD that requires a mass of sense-annotated data. HowNet is the most widely used lexical knowledge base in Chinese WSD. Because of its uniqueness, however, most of existing unsupervised WSD methods cannot work for HowNet-based WSD, and the tailor-made methods have not obtained satisfying results. In this paper, we propose a new unsupervised method for HowNet-based Chinese WSD, which exploits the masked language model task of pre-trained language models. In experiments, considering existing evaluation dataset is small and out-of-date, we build a new and larger HowNet-based WSD dataset. Experimental results demonstrate that our model achieves significantly better performance than all the baseline methods. All the code and data of this paper are available at \url{https://github.com/thunlp/SememeWSD}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hou-etal-2020-try">
<titleInfo>
<title>Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bairu</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanchao</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Zang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xurui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word sense disambiguation (WSD) is a fundamental natural language processing task. Unsupervised knowledge-based WSD only relies on a lexical knowledge base as the sense inventory and has wider practical use than supervised WSD that requires a mass of sense-annotated data. HowNet is the most widely used lexical knowledge base in Chinese WSD. Because of its uniqueness, however, most of existing unsupervised WSD methods cannot work for HowNet-based WSD, and the tailor-made methods have not obtained satisfying results. In this paper, we propose a new unsupervised method for HowNet-based Chinese WSD, which exploits the masked language model task of pre-trained language models. In experiments, considering existing evaluation dataset is small and out-of-date, we build a new and larger HowNet-based WSD dataset. Experimental results demonstrate that our model achieves significantly better performance than all the baseline methods. All the code and data of this paper are available at https://github.com/thunlp/SememeWSD.</abstract>
<identifier type="citekey">hou-etal-2020-try</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.155</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.155/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1752</start>
<end>1757</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet
%A Hou, Bairu
%A Qi, Fanchao
%A Zang, Yuan
%A Zhang, Xurui
%A Liu, Zhiyuan
%A Sun, Maosong
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F hou-etal-2020-try
%X Word sense disambiguation (WSD) is a fundamental natural language processing task. Unsupervised knowledge-based WSD only relies on a lexical knowledge base as the sense inventory and has wider practical use than supervised WSD that requires a mass of sense-annotated data. HowNet is the most widely used lexical knowledge base in Chinese WSD. Because of its uniqueness, however, most of existing unsupervised WSD methods cannot work for HowNet-based WSD, and the tailor-made methods have not obtained satisfying results. In this paper, we propose a new unsupervised method for HowNet-based Chinese WSD, which exploits the masked language model task of pre-trained language models. In experiments, considering existing evaluation dataset is small and out-of-date, we build a new and larger HowNet-based WSD dataset. Experimental results demonstrate that our model achieves significantly better performance than all the baseline methods. All the code and data of this paper are available at https://github.com/thunlp/SememeWSD.
%R 10.18653/v1/2020.coling-main.155
%U https://aclanthology.org/2020.coling-main.155/
%U https://doi.org/10.18653/v1/2020.coling-main.155
%P 1752-1757
Markdown (Informal)
[Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet](https://aclanthology.org/2020.coling-main.155/) (Hou et al., COLING 2020)
- Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet (Hou et al., COLING 2020)
ACL
- Bairu Hou, Fanchao Qi, Yuan Zang, Xurui Zhang, Zhiyuan Liu, and Maosong Sun. 2020. Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1752–1757, Barcelona, Spain (Online). International Committee on Computational Linguistics.