@inproceedings{yoon-etal-2022-smsmix,
title = "{SMSM}ix: Sense-Maintained Sentence Mixup for Word Sense Disambiguation",
author = "Yoon, Hee Suk and
Yoon, Eunseop and
Harvill, John and
Yoon, Sunjae and
Hasegawa-Johnson, Mark and
Yoo, Chang",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.107",
doi = "10.18653/v1/2022.findings-emnlp.107",
pages = "1493--1502",
abstract = "Word Sense Disambiguation (WSD) is an NLP task aimed at determining the correct sense of a word in a sentence from discrete sense choices. Although current systems have attained unprecedented performances for such tasks, the nonuniform distribution of word senses during training generally results in systems performing poorly on rare senses. To this end, we consider data augmentation to increase the frequency of these least frequent senses (LFS) to reduce the distributional bias of senses during training. We propose Sense-Maintained Sentence Mixup (SMSMix), a novel word-level mixup method that maintains the sense of a target word. SMSMix smoothly blends two sentences using mask prediction while preserving the relevant span determined by saliency scores to maintain a specific word{'}s sense. To the best of our knowledge, this is the first attempt to apply mixup in NLP while preserving the meaning of a specific word. With extensive experiments, we validate that our augmentation method can effectively give more information about rare senses during training with maintained target sense label.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yoon-etal-2022-smsmix">
<titleInfo>
<title>SMSMix: Sense-Maintained Sentence Mixup for Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hee</namePart>
<namePart type="given">Suk</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunseop</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Harvill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunjae</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Hasegawa-Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Yoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word Sense Disambiguation (WSD) is an NLP task aimed at determining the correct sense of a word in a sentence from discrete sense choices. Although current systems have attained unprecedented performances for such tasks, the nonuniform distribution of word senses during training generally results in systems performing poorly on rare senses. To this end, we consider data augmentation to increase the frequency of these least frequent senses (LFS) to reduce the distributional bias of senses during training. We propose Sense-Maintained Sentence Mixup (SMSMix), a novel word-level mixup method that maintains the sense of a target word. SMSMix smoothly blends two sentences using mask prediction while preserving the relevant span determined by saliency scores to maintain a specific word’s sense. To the best of our knowledge, this is the first attempt to apply mixup in NLP while preserving the meaning of a specific word. With extensive experiments, we validate that our augmentation method can effectively give more information about rare senses during training with maintained target sense label.</abstract>
<identifier type="citekey">yoon-etal-2022-smsmix</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.107</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.107</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1493</start>
<end>1502</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SMSMix: Sense-Maintained Sentence Mixup for Word Sense Disambiguation
%A Yoon, Hee Suk
%A Yoon, Eunseop
%A Harvill, John
%A Yoon, Sunjae
%A Hasegawa-Johnson, Mark
%A Yoo, Chang
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F yoon-etal-2022-smsmix
%X Word Sense Disambiguation (WSD) is an NLP task aimed at determining the correct sense of a word in a sentence from discrete sense choices. Although current systems have attained unprecedented performances for such tasks, the nonuniform distribution of word senses during training generally results in systems performing poorly on rare senses. To this end, we consider data augmentation to increase the frequency of these least frequent senses (LFS) to reduce the distributional bias of senses during training. We propose Sense-Maintained Sentence Mixup (SMSMix), a novel word-level mixup method that maintains the sense of a target word. SMSMix smoothly blends two sentences using mask prediction while preserving the relevant span determined by saliency scores to maintain a specific word’s sense. To the best of our knowledge, this is the first attempt to apply mixup in NLP while preserving the meaning of a specific word. With extensive experiments, we validate that our augmentation method can effectively give more information about rare senses during training with maintained target sense label.
%R 10.18653/v1/2022.findings-emnlp.107
%U https://aclanthology.org/2022.findings-emnlp.107
%U https://doi.org/10.18653/v1/2022.findings-emnlp.107
%P 1493-1502
Markdown (Informal)
[SMSMix: Sense-Maintained Sentence Mixup for Word Sense Disambiguation](https://aclanthology.org/2022.findings-emnlp.107) (Yoon et al., Findings 2022)
ACL