@inproceedings{wang-etal-2024-refining,
title = "Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis",
author = "Wang, Haining and
He, Kang and
Li, Bobo and
Chen, Lei and
Li, Fei and
Han, Xu and
Teng, Chong and
Ji, Donghong",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.615/",
doi = "10.18653/v1/2024.findings-acl.615",
pages = "10318--10329",
abstract = "Aspect-based Sentiment Analysis (ABSA) is extensively researched in the NLP community, yet related models face challenges due to data sparsity when shifting to a new domain. Hence, data augmentation for cross-domain ABSA has attracted increasing attention in recent years. However, two key points have been neglected in prior studies: First, target domain unlabeled data are labeled with pseudo labels by the model trained in the source domain with little quality control, leading to inaccuracy and error propagation. Second, the label and text patterns of generated labeled data are monotonous, thus limiting the robustness and generalization ability of trained ABSA models. In this paper, we aim to design a simple yet effective framework to address the above shortages in ABSA data augmentation, called Refining and Synthesis Data Augmentation (RSDA). Our framework roughly includes two steps: First, it refines generated labeled data using a natural language inference (NLI) filter to control data quality. Second, it synthesizes diverse labeled data via novel label composition and paraphrase approaches. We conduct experiments on 4 kinds of ABSA subtasks, and our framework outperforms 7 strong baselines, demonstrating its effectiveness."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-refining">
<titleInfo>
<title>Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haining</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bobo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Teng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Aspect-based Sentiment Analysis (ABSA) is extensively researched in the NLP community, yet related models face challenges due to data sparsity when shifting to a new domain. Hence, data augmentation for cross-domain ABSA has attracted increasing attention in recent years. However, two key points have been neglected in prior studies: First, target domain unlabeled data are labeled with pseudo labels by the model trained in the source domain with little quality control, leading to inaccuracy and error propagation. Second, the label and text patterns of generated labeled data are monotonous, thus limiting the robustness and generalization ability of trained ABSA models. In this paper, we aim to design a simple yet effective framework to address the above shortages in ABSA data augmentation, called Refining and Synthesis Data Augmentation (RSDA). Our framework roughly includes two steps: First, it refines generated labeled data using a natural language inference (NLI) filter to control data quality. Second, it synthesizes diverse labeled data via novel label composition and paraphrase approaches. We conduct experiments on 4 kinds of ABSA subtasks, and our framework outperforms 7 strong baselines, demonstrating its effectiveness.</abstract>
<identifier type="citekey">wang-etal-2024-refining</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.615</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.615/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10318</start>
<end>10329</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis
%A Wang, Haining
%A He, Kang
%A Li, Bobo
%A Chen, Lei
%A Li, Fei
%A Han, Xu
%A Teng, Chong
%A Ji, Donghong
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-refining
%X Aspect-based Sentiment Analysis (ABSA) is extensively researched in the NLP community, yet related models face challenges due to data sparsity when shifting to a new domain. Hence, data augmentation for cross-domain ABSA has attracted increasing attention in recent years. However, two key points have been neglected in prior studies: First, target domain unlabeled data are labeled with pseudo labels by the model trained in the source domain with little quality control, leading to inaccuracy and error propagation. Second, the label and text patterns of generated labeled data are monotonous, thus limiting the robustness and generalization ability of trained ABSA models. In this paper, we aim to design a simple yet effective framework to address the above shortages in ABSA data augmentation, called Refining and Synthesis Data Augmentation (RSDA). Our framework roughly includes two steps: First, it refines generated labeled data using a natural language inference (NLI) filter to control data quality. Second, it synthesizes diverse labeled data via novel label composition and paraphrase approaches. We conduct experiments on 4 kinds of ABSA subtasks, and our framework outperforms 7 strong baselines, demonstrating its effectiveness.
%R 10.18653/v1/2024.findings-acl.615
%U https://aclanthology.org/2024.findings-acl.615/
%U https://doi.org/10.18653/v1/2024.findings-acl.615
%P 10318-10329
Markdown (Informal)
[Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis](https://aclanthology.org/2024.findings-acl.615/) (Wang et al., Findings 2024)
ACL
- Haining Wang, Kang He, Bobo Li, Lei Chen, Fei Li, Xu Han, Chong Teng, and Donghong Ji. 2024. Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10318–10329, Bangkok, Thailand. Association for Computational Linguistics.