@inproceedings{shen-etal-2023-simple,
title = "Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization",
author = "Shen, Ming and
Ma, Jie and
Wang, Shuai and
Vyas, Yogarshi and
Dixit, Kalpit and
Ballesteros, Miguel and
Benajiba, Yassine",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.142",
doi = "10.18653/v1/2023.findings-eacl.142",
pages = "1898--1911",
abstract = "Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews. However, generating aspect-specific and general summaries is challenging due to the lack of annotated data. In this work, we propose two simple yet effective unsupervised approaches to generate both aspect-specific and general opinion summaries by training on synthetic datasets constructed with aspect-related review contents. Our first approach, Seed Words Based Leave-One-Out (SW-LOO), identifies aspect-related portions of reviews simply by exact-matching aspect seed words and outperforms existing methods by 3.4 ROUGE-L points on Space and 0.5 ROUGE-1 point on Oposum+ for aspect-specific opinion summarization. Our second approach, Natural Language Inference Based Leave-One-Out (NLI-LOO) identifies aspect-related sentences utilizing an NLI model in a more general setting without using seed words and outperforms existing approaches by 1.2 ROUGE-L points on Space for aspect-specific opinion summarization and remains competitive on other metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2023-simple">
<titleInfo>
<title>Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yogarshi</namePart>
<namePart type="family">Vyas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalpit</namePart>
<namePart type="family">Dixit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Ballesteros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yassine</namePart>
<namePart type="family">Benajiba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews. However, generating aspect-specific and general summaries is challenging due to the lack of annotated data. In this work, we propose two simple yet effective unsupervised approaches to generate both aspect-specific and general opinion summaries by training on synthetic datasets constructed with aspect-related review contents. Our first approach, Seed Words Based Leave-One-Out (SW-LOO), identifies aspect-related portions of reviews simply by exact-matching aspect seed words and outperforms existing methods by 3.4 ROUGE-L points on Space and 0.5 ROUGE-1 point on Oposum+ for aspect-specific opinion summarization. Our second approach, Natural Language Inference Based Leave-One-Out (NLI-LOO) identifies aspect-related sentences utilizing an NLI model in a more general setting without using seed words and outperforms existing approaches by 1.2 ROUGE-L points on Space for aspect-specific opinion summarization and remains competitive on other metrics.</abstract>
<identifier type="citekey">shen-etal-2023-simple</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.142</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.142</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1898</start>
<end>1911</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization
%A Shen, Ming
%A Ma, Jie
%A Wang, Shuai
%A Vyas, Yogarshi
%A Dixit, Kalpit
%A Ballesteros, Miguel
%A Benajiba, Yassine
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F shen-etal-2023-simple
%X Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews. However, generating aspect-specific and general summaries is challenging due to the lack of annotated data. In this work, we propose two simple yet effective unsupervised approaches to generate both aspect-specific and general opinion summaries by training on synthetic datasets constructed with aspect-related review contents. Our first approach, Seed Words Based Leave-One-Out (SW-LOO), identifies aspect-related portions of reviews simply by exact-matching aspect seed words and outperforms existing methods by 3.4 ROUGE-L points on Space and 0.5 ROUGE-1 point on Oposum+ for aspect-specific opinion summarization. Our second approach, Natural Language Inference Based Leave-One-Out (NLI-LOO) identifies aspect-related sentences utilizing an NLI model in a more general setting without using seed words and outperforms existing approaches by 1.2 ROUGE-L points on Space for aspect-specific opinion summarization and remains competitive on other metrics.
%R 10.18653/v1/2023.findings-eacl.142
%U https://aclanthology.org/2023.findings-eacl.142
%U https://doi.org/10.18653/v1/2023.findings-eacl.142
%P 1898-1911
Markdown (Informal)
[Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization](https://aclanthology.org/2023.findings-eacl.142) (Shen et al., Findings 2023)
ACL