@inproceedings{zhang-etal-2022-word,
title = "Word Sense Disambiguation with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension",
author = "Zhang, Guobiao and
Lu, Wenpeng and
Peng, Xueping and
Wang, Shoujin and
Kan, Baoshuo and
Yu, Rui",
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-1.357",
pages = "4061--4070",
abstract = "Word sense disambiguation (WSD), identifying the most suitable meaning of ambiguous words in the given contexts according to a predefined sense inventory, is one of the most classical and challenging tasks in natural language processing. Benefiting from the powerful ability of deep neural networks, WSD has achieved a great advancement in recent years. Reformulating WSD as a text span extraction task is an effective approach, which accepts a sentence context of an ambiguous word together with all definitions of its candidate senses simultaneously, and requires to extract the text span corresponding with the right sense. However, the approach merely depends on a short definition to learn sense representation, which neglects abundant semantic knowledge from related senses and leads to data-inefficient learning and suboptimal WSD performance. To address the limitations, we propose a novel WSD method with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension (KELESC). Specifically, a knowledge-enhanced method is proposed to enrich semantic representation by incorporating additional examples and definitions of the related senses in WordNet. Then, in order to avoid the huge computing complexity induced by the additional information, a local self-attention mechanism is utilized to constrain attention to be local, which allows longer input texts without large-scale computing burdens. Extensive experimental results demonstrate that KELESC achieves better performance than baseline models on public benchmark datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-word">
<titleInfo>
<title>Word Sense Disambiguation with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guobiao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenpeng</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueping</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shoujin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baoshuo</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Yu</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>Word sense disambiguation (WSD), identifying the most suitable meaning of ambiguous words in the given contexts according to a predefined sense inventory, is one of the most classical and challenging tasks in natural language processing. Benefiting from the powerful ability of deep neural networks, WSD has achieved a great advancement in recent years. Reformulating WSD as a text span extraction task is an effective approach, which accepts a sentence context of an ambiguous word together with all definitions of its candidate senses simultaneously, and requires to extract the text span corresponding with the right sense. However, the approach merely depends on a short definition to learn sense representation, which neglects abundant semantic knowledge from related senses and leads to data-inefficient learning and suboptimal WSD performance. To address the limitations, we propose a novel WSD method with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension (KELESC). Specifically, a knowledge-enhanced method is proposed to enrich semantic representation by incorporating additional examples and definitions of the related senses in WordNet. Then, in order to avoid the huge computing complexity induced by the additional information, a local self-attention mechanism is utilized to constrain attention to be local, which allows longer input texts without large-scale computing burdens. Extensive experimental results demonstrate that KELESC achieves better performance than baseline models on public benchmark datasets.</abstract>
<identifier type="citekey">zhang-etal-2022-word</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.357</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4061</start>
<end>4070</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Sense Disambiguation with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension
%A Zhang, Guobiao
%A Lu, Wenpeng
%A Peng, Xueping
%A Wang, Shoujin
%A Kan, Baoshuo
%A Yu, Rui
%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 zhang-etal-2022-word
%X Word sense disambiguation (WSD), identifying the most suitable meaning of ambiguous words in the given contexts according to a predefined sense inventory, is one of the most classical and challenging tasks in natural language processing. Benefiting from the powerful ability of deep neural networks, WSD has achieved a great advancement in recent years. Reformulating WSD as a text span extraction task is an effective approach, which accepts a sentence context of an ambiguous word together with all definitions of its candidate senses simultaneously, and requires to extract the text span corresponding with the right sense. However, the approach merely depends on a short definition to learn sense representation, which neglects abundant semantic knowledge from related senses and leads to data-inefficient learning and suboptimal WSD performance. To address the limitations, we propose a novel WSD method with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension (KELESC). Specifically, a knowledge-enhanced method is proposed to enrich semantic representation by incorporating additional examples and definitions of the related senses in WordNet. Then, in order to avoid the huge computing complexity induced by the additional information, a local self-attention mechanism is utilized to constrain attention to be local, which allows longer input texts without large-scale computing burdens. Extensive experimental results demonstrate that KELESC achieves better performance than baseline models on public benchmark datasets.
%U https://aclanthology.org/2022.coling-1.357
%P 4061-4070
Markdown (Informal)
[Word Sense Disambiguation with Knowledge-Enhanced and Local Self-Attention-based Extractive Sense Comprehension](https://aclanthology.org/2022.coling-1.357) (Zhang et al., COLING 2022)
ACL