@inproceedings{chen-etal-2022-unsupervised-data,
title = "Unsupervised Data Augmentation for Aspect Based Sentiment Analysis",
author = "Chen, David Z. and
Faulkner, Adam and
Badyal, Sahil",
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-1.586",
pages = "6746--6751",
abstract = "Recent approaches to Aspect-based Sentiment Analysis (ABSA) take a co-extraction approach to this span-level classification task, performing the subtasks of aspect term extraction (ATE) and aspect sentiment classification (ASC) simultaneously. In this work, we build on recent progress in applying pre-training to this co-extraction task with the introduction of an adaptation of Unsupervised Data Augmentation in semi-supervised learning. As originally implemented, UDA cannot accommodate span-level classification since it relies on advanced data augmentation techniques, such as back-translation, that alter the sequence lengths of the original data and cause index mismatches. We introduce an adaptation of UDA using Masked Language Model (MLM) unmasking that accommodates this index-match constraint and test the approach on standard ABSA benchmark datasets. We show that simple augmentations applied to modest-sized datasets along with consistency training lead to competitive performance with the current ABSA state-of-the-art in the restaurant and laptop domains using only 75{\%} of the training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-unsupervised-data">
<titleInfo>
<title>Unsupervised Data Augmentation for Aspect Based Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Z</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Faulkner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahil</namePart>
<namePart type="family">Badyal</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>Recent approaches to Aspect-based Sentiment Analysis (ABSA) take a co-extraction approach to this span-level classification task, performing the subtasks of aspect term extraction (ATE) and aspect sentiment classification (ASC) simultaneously. In this work, we build on recent progress in applying pre-training to this co-extraction task with the introduction of an adaptation of Unsupervised Data Augmentation in semi-supervised learning. As originally implemented, UDA cannot accommodate span-level classification since it relies on advanced data augmentation techniques, such as back-translation, that alter the sequence lengths of the original data and cause index mismatches. We introduce an adaptation of UDA using Masked Language Model (MLM) unmasking that accommodates this index-match constraint and test the approach on standard ABSA benchmark datasets. We show that simple augmentations applied to modest-sized datasets along with consistency training lead to competitive performance with the current ABSA state-of-the-art in the restaurant and laptop domains using only 75% of the training data.</abstract>
<identifier type="citekey">chen-etal-2022-unsupervised-data</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.586</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>6746</start>
<end>6751</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Data Augmentation for Aspect Based Sentiment Analysis
%A Chen, David Z.
%A Faulkner, Adam
%A Badyal, Sahil
%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 chen-etal-2022-unsupervised-data
%X Recent approaches to Aspect-based Sentiment Analysis (ABSA) take a co-extraction approach to this span-level classification task, performing the subtasks of aspect term extraction (ATE) and aspect sentiment classification (ASC) simultaneously. In this work, we build on recent progress in applying pre-training to this co-extraction task with the introduction of an adaptation of Unsupervised Data Augmentation in semi-supervised learning. As originally implemented, UDA cannot accommodate span-level classification since it relies on advanced data augmentation techniques, such as back-translation, that alter the sequence lengths of the original data and cause index mismatches. We introduce an adaptation of UDA using Masked Language Model (MLM) unmasking that accommodates this index-match constraint and test the approach on standard ABSA benchmark datasets. We show that simple augmentations applied to modest-sized datasets along with consistency training lead to competitive performance with the current ABSA state-of-the-art in the restaurant and laptop domains using only 75% of the training data.
%U https://aclanthology.org/2022.coling-1.586
%P 6746-6751
Markdown (Informal)
[Unsupervised Data Augmentation for Aspect Based Sentiment Analysis](https://aclanthology.org/2022.coling-1.586) (Chen et al., COLING 2022)
ACL