@inproceedings{li-etal-2022-generative,
title = "Generative Cross-Domain Data Augmentation for Aspect and Opinion Co-Extraction",
author = "Li, Junjie and
Yu, Jianfei and
Xia, Rui",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.312",
doi = "10.18653/v1/2022.naacl-main.312",
pages = "4219--4229",
abstract = "As a fundamental task in opinion mining, aspect and opinion co-extraction aims to identify the aspect terms and opinion terms in reviews. However, due to the lack of fine-grained annotated resources, it is hard to train a robust model for many domains. To alleviate this issue, unsupervised domain adaptation is proposed to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we propose a new Generative Cross-Domain Data Augmentation framework for unsupervised domain adaptation. The proposed framework is aimed to generate target-domain data with fine-grained annotation by exploiting the labeled data in the source domain. Specifically, we remove the domain-specific segments in a source-domain labeled sentence, and then use this as input to a pre-trained sequence-to-sequence model BART to simultaneously generate a target-domain sentence and predict the corresponding label for each word. Experimental results on three datasets demonstrate that our approach is more effective than previous domain adaptation methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-generative">
<titleInfo>
<title>Generative Cross-Domain Data Augmentation for Aspect and Opinion Co-Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfei</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As a fundamental task in opinion mining, aspect and opinion co-extraction aims to identify the aspect terms and opinion terms in reviews. However, due to the lack of fine-grained annotated resources, it is hard to train a robust model for many domains. To alleviate this issue, unsupervised domain adaptation is proposed to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we propose a new Generative Cross-Domain Data Augmentation framework for unsupervised domain adaptation. The proposed framework is aimed to generate target-domain data with fine-grained annotation by exploiting the labeled data in the source domain. Specifically, we remove the domain-specific segments in a source-domain labeled sentence, and then use this as input to a pre-trained sequence-to-sequence model BART to simultaneously generate a target-domain sentence and predict the corresponding label for each word. Experimental results on three datasets demonstrate that our approach is more effective than previous domain adaptation methods.</abstract>
<identifier type="citekey">li-etal-2022-generative</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.312</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.312</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>4219</start>
<end>4229</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generative Cross-Domain Data Augmentation for Aspect and Opinion Co-Extraction
%A Li, Junjie
%A Yu, Jianfei
%A Xia, Rui
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F li-etal-2022-generative
%X As a fundamental task in opinion mining, aspect and opinion co-extraction aims to identify the aspect terms and opinion terms in reviews. However, due to the lack of fine-grained annotated resources, it is hard to train a robust model for many domains. To alleviate this issue, unsupervised domain adaptation is proposed to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we propose a new Generative Cross-Domain Data Augmentation framework for unsupervised domain adaptation. The proposed framework is aimed to generate target-domain data with fine-grained annotation by exploiting the labeled data in the source domain. Specifically, we remove the domain-specific segments in a source-domain labeled sentence, and then use this as input to a pre-trained sequence-to-sequence model BART to simultaneously generate a target-domain sentence and predict the corresponding label for each word. Experimental results on three datasets demonstrate that our approach is more effective than previous domain adaptation methods.
%R 10.18653/v1/2022.naacl-main.312
%U https://aclanthology.org/2022.naacl-main.312
%U https://doi.org/10.18653/v1/2022.naacl-main.312
%P 4219-4229
Markdown (Informal)
[Generative Cross-Domain Data Augmentation for Aspect and Opinion Co-Extraction](https://aclanthology.org/2022.naacl-main.312) (Li et al., NAACL 2022)
ACL