@inproceedings{yap-etal-2020-adapting,
title = "Adapting {BERT} for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences",
author = "Yap, Boon Peng and
Koh, Andrew and
Chng, Eng Siong",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.4",
doi = "10.18653/v1/2020.findings-emnlp.4",
pages = "41--46",
abstract = "Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a relevance ranking task, and fine-tune BERT on sequence-pair ranking task to select the most probable sense definition given a context sentence and a list of candidate sense definitions. We also introduce a data augmentation technique for WSD using existing example sentences from WordNet. Using the proposed training objective and data augmentation technique, our models are able to achieve state-of-the-art results on the English all-words benchmark datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yap-etal-2020-adapting">
<titleInfo>
<title>Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boon</namePart>
<namePart type="given">Peng</namePart>
<namePart type="family">Yap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Koh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eng</namePart>
<namePart type="given">Siong</namePart>
<namePart type="family">Chng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a relevance ranking task, and fine-tune BERT on sequence-pair ranking task to select the most probable sense definition given a context sentence and a list of candidate sense definitions. We also introduce a data augmentation technique for WSD using existing example sentences from WordNet. Using the proposed training objective and data augmentation technique, our models are able to achieve state-of-the-art results on the English all-words benchmark datasets.</abstract>
<identifier type="citekey">yap-etal-2020-adapting</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.4</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.4</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>41</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences
%A Yap, Boon Peng
%A Koh, Andrew
%A Chng, Eng Siong
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F yap-etal-2020-adapting
%X Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a relevance ranking task, and fine-tune BERT on sequence-pair ranking task to select the most probable sense definition given a context sentence and a list of candidate sense definitions. We also introduce a data augmentation technique for WSD using existing example sentences from WordNet. Using the proposed training objective and data augmentation technique, our models are able to achieve state-of-the-art results on the English all-words benchmark datasets.
%R 10.18653/v1/2020.findings-emnlp.4
%U https://aclanthology.org/2020.findings-emnlp.4
%U https://doi.org/10.18653/v1/2020.findings-emnlp.4
%P 41-46
Markdown (Informal)
[Adapting BERT for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences](https://aclanthology.org/2020.findings-emnlp.4) (Yap et al., Findings 2020)
ACL