@inproceedings{peper-wang-2022-generative,
title = "Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure",
author = "Peper, Joseph and
Wang, Lu",
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.451",
doi = "10.18653/v1/2022.findings-emnlp.451",
pages = "6089--6095",
abstract = "Generative models have demonstrated impressive results on Aspect-based Sentiment Analysis (ABSA) tasks, particularly for the emerging task of extracting Aspect-Category-Opinion-Sentiment (ACOS) quadruples. However, these models struggle with implicit sentiment expressions, which are commonly observed in opinionated content such as online reviews. In this work, we introduce GEN-SCL-NAT, which consists of two techniques for improved structured generation for ACOS quadruple extraction. First, we propose GEN-SCL, a supervised contrastive learning objective that aids quadruple prediction by encouraging the model to produce input representations that are discriminable across key input attributes, such as sentiment polarity and the existence of implicit opinions and aspects. Second, we introduce GEN-NAT, a new structured generation format that better adapts pre-trained autoregressive encoder-decoder models to extract quadruples in a generative fashion. Experimental results show that GEN-SCL-NAT achieves top performance across three ACOS datasets, averaging 1.48{\%} F1 improvement, with a maximum 1.73{\%} increase on the LAPTOP-L1 dataset. Additionally, we see significant gains on implicit aspect and opinion splits that have been shown as challenging for existing ACOS approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peper-wang-2022-generative">
<titleInfo>
<title>Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Peper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</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>Generative models have demonstrated impressive results on Aspect-based Sentiment Analysis (ABSA) tasks, particularly for the emerging task of extracting Aspect-Category-Opinion-Sentiment (ACOS) quadruples. However, these models struggle with implicit sentiment expressions, which are commonly observed in opinionated content such as online reviews. In this work, we introduce GEN-SCL-NAT, which consists of two techniques for improved structured generation for ACOS quadruple extraction. First, we propose GEN-SCL, a supervised contrastive learning objective that aids quadruple prediction by encouraging the model to produce input representations that are discriminable across key input attributes, such as sentiment polarity and the existence of implicit opinions and aspects. Second, we introduce GEN-NAT, a new structured generation format that better adapts pre-trained autoregressive encoder-decoder models to extract quadruples in a generative fashion. Experimental results show that GEN-SCL-NAT achieves top performance across three ACOS datasets, averaging 1.48% F1 improvement, with a maximum 1.73% increase on the LAPTOP-L1 dataset. Additionally, we see significant gains on implicit aspect and opinion splits that have been shown as challenging for existing ACOS approaches.</abstract>
<identifier type="citekey">peper-wang-2022-generative</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.451</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.451</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6089</start>
<end>6095</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure
%A Peper, Joseph
%A Wang, Lu
%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 peper-wang-2022-generative
%X Generative models have demonstrated impressive results on Aspect-based Sentiment Analysis (ABSA) tasks, particularly for the emerging task of extracting Aspect-Category-Opinion-Sentiment (ACOS) quadruples. However, these models struggle with implicit sentiment expressions, which are commonly observed in opinionated content such as online reviews. In this work, we introduce GEN-SCL-NAT, which consists of two techniques for improved structured generation for ACOS quadruple extraction. First, we propose GEN-SCL, a supervised contrastive learning objective that aids quadruple prediction by encouraging the model to produce input representations that are discriminable across key input attributes, such as sentiment polarity and the existence of implicit opinions and aspects. Second, we introduce GEN-NAT, a new structured generation format that better adapts pre-trained autoregressive encoder-decoder models to extract quadruples in a generative fashion. Experimental results show that GEN-SCL-NAT achieves top performance across three ACOS datasets, averaging 1.48% F1 improvement, with a maximum 1.73% increase on the LAPTOP-L1 dataset. Additionally, we see significant gains on implicit aspect and opinion splits that have been shown as challenging for existing ACOS approaches.
%R 10.18653/v1/2022.findings-emnlp.451
%U https://aclanthology.org/2022.findings-emnlp.451
%U https://doi.org/10.18653/v1/2022.findings-emnlp.451
%P 6089-6095
Markdown (Informal)
[Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure](https://aclanthology.org/2022.findings-emnlp.451) (Peper & Wang, Findings 2022)
ACL