@inproceedings{zhou-etal-2019-bert,
title = "{BERT}-based Lexical Substitution",
author = "Zhou, Wangchunshu and
Ge, Tao and
Xu, Ke and
Wei, Furu and
Zhou, Ming",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1328",
doi = "10.18653/v1/P19-1328",
pages = "3368--3373",
abstract = "Previous studies on lexical substitution tend to obtain substitute candidates by finding the target word{'}s synonyms from lexical resources (e.g., WordNet) and then rank the candidates based on its contexts. These approaches have two limitations: (1) They are likely to overlook good substitute candidates that are not the synonyms of the target words in the lexical resources; (2) They fail to take into account the substitution{'}s influence on the global context of the sentence. To address these issues, we propose an end-to-end BERT-based lexical substitution approach which can propose and validate substitute candidates without using any annotated data or manually curated resources. Our approach first applies dropout to the target word{'}s embedding for partially masking the word, allowing BERT to take balanced consideration of the target word{'}s semantics and contexts for proposing substitute candidates, and then validates the candidates based on their substitution{'}s influence on the global contextualized representation of the sentence. Experiments show our approach performs well in both proposing and ranking substitute candidates, achieving the state-of-the-art results in both LS07 and LS14 benchmarks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2019-bert">
<titleInfo>
<title>BERT-based Lexical Substitution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wangchunshu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Furu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous studies on lexical substitution tend to obtain substitute candidates by finding the target word’s synonyms from lexical resources (e.g., WordNet) and then rank the candidates based on its contexts. These approaches have two limitations: (1) They are likely to overlook good substitute candidates that are not the synonyms of the target words in the lexical resources; (2) They fail to take into account the substitution’s influence on the global context of the sentence. To address these issues, we propose an end-to-end BERT-based lexical substitution approach which can propose and validate substitute candidates without using any annotated data or manually curated resources. Our approach first applies dropout to the target word’s embedding for partially masking the word, allowing BERT to take balanced consideration of the target word’s semantics and contexts for proposing substitute candidates, and then validates the candidates based on their substitution’s influence on the global contextualized representation of the sentence. Experiments show our approach performs well in both proposing and ranking substitute candidates, achieving the state-of-the-art results in both LS07 and LS14 benchmarks.</abstract>
<identifier type="citekey">zhou-etal-2019-bert</identifier>
<identifier type="doi">10.18653/v1/P19-1328</identifier>
<location>
<url>https://aclanthology.org/P19-1328</url>
</location>
<part>
<date>2019-jul</date>
<extent unit="page">
<start>3368</start>
<end>3373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERT-based Lexical Substitution
%A Zhou, Wangchunshu
%A Ge, Tao
%A Xu, Ke
%A Wei, Furu
%A Zhou, Ming
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 jul
%I Association for Computational Linguistics
%C Florence, Italy
%F zhou-etal-2019-bert
%X Previous studies on lexical substitution tend to obtain substitute candidates by finding the target word’s synonyms from lexical resources (e.g., WordNet) and then rank the candidates based on its contexts. These approaches have two limitations: (1) They are likely to overlook good substitute candidates that are not the synonyms of the target words in the lexical resources; (2) They fail to take into account the substitution’s influence on the global context of the sentence. To address these issues, we propose an end-to-end BERT-based lexical substitution approach which can propose and validate substitute candidates without using any annotated data or manually curated resources. Our approach first applies dropout to the target word’s embedding for partially masking the word, allowing BERT to take balanced consideration of the target word’s semantics and contexts for proposing substitute candidates, and then validates the candidates based on their substitution’s influence on the global contextualized representation of the sentence. Experiments show our approach performs well in both proposing and ranking substitute candidates, achieving the state-of-the-art results in both LS07 and LS14 benchmarks.
%R 10.18653/v1/P19-1328
%U https://aclanthology.org/P19-1328
%U https://doi.org/10.18653/v1/P19-1328
%P 3368-3373
Markdown (Informal)
[BERT-based Lexical Substitution](https://aclanthology.org/P19-1328) (Zhou et al., ACL 2019)
ACL
- Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, and Ming Zhou. 2019. BERT-based Lexical Substitution. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3368–3373, Florence, Italy. Association for Computational Linguistics.