@inproceedings{sim-etal-2022-empirical,
title = "An Empirical Study on Topic Preservation in Multi-Document Summarization",
author = "Sim, Mong Yuan and
Zhang, Wei Emma and
Ma, Congbo",
editor = "Hanqi, Yan and
Zonghan, Yang and
Ruder, Sebastian and
Xiaojun, Wan",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Student Research Workshop",
month = nov,
year = "2022",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-srw.9",
pages = "61--67",
abstract = "Multi-document summarization (MDS) is a process of generating an informative and concise summary from multiple topic-related documents. Many studies have analyzed the quality of MDS dataset or models, however no work has been done from the perspective of topic preservation. In this work, we fill the gap by performing an empirical analysis on two MDS datasets and study topic preservation on generated summaries from 8 MDS models. Our key findings include i) Multi-News dataset has better gold summaries compared to Multi-XScience in terms of its topic distribution consistency and ii) Extractive approaches perform better than abstractive approaches in preserving topic information from source documents. We hope our findings could help develop a summarization model that can generate topic-focused summary and also give inspiration to researchers in creating dataset for such challenging task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sim-etal-2022-empirical">
<titleInfo>
<title>An Empirical Study on Topic Preservation in Multi-Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mong</namePart>
<namePart type="given">Yuan</namePart>
<namePart type="family">Sim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="given">Emma</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Congbo</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Hanqi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zonghan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wan</namePart>
<namePart type="family">Xiaojun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-document summarization (MDS) is a process of generating an informative and concise summary from multiple topic-related documents. Many studies have analyzed the quality of MDS dataset or models, however no work has been done from the perspective of topic preservation. In this work, we fill the gap by performing an empirical analysis on two MDS datasets and study topic preservation on generated summaries from 8 MDS models. Our key findings include i) Multi-News dataset has better gold summaries compared to Multi-XScience in terms of its topic distribution consistency and ii) Extractive approaches perform better than abstractive approaches in preserving topic information from source documents. We hope our findings could help develop a summarization model that can generate topic-focused summary and also give inspiration to researchers in creating dataset for such challenging task.</abstract>
<identifier type="citekey">sim-etal-2022-empirical</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-srw.9</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>61</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Study on Topic Preservation in Multi-Document Summarization
%A Sim, Mong Yuan
%A Zhang, Wei Emma
%A Ma, Congbo
%Y Hanqi, Yan
%Y Zonghan, Yang
%Y Ruder, Sebastian
%Y Xiaojun, Wan
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Student Research Workshop
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online
%F sim-etal-2022-empirical
%X Multi-document summarization (MDS) is a process of generating an informative and concise summary from multiple topic-related documents. Many studies have analyzed the quality of MDS dataset or models, however no work has been done from the perspective of topic preservation. In this work, we fill the gap by performing an empirical analysis on two MDS datasets and study topic preservation on generated summaries from 8 MDS models. Our key findings include i) Multi-News dataset has better gold summaries compared to Multi-XScience in terms of its topic distribution consistency and ii) Extractive approaches perform better than abstractive approaches in preserving topic information from source documents. We hope our findings could help develop a summarization model that can generate topic-focused summary and also give inspiration to researchers in creating dataset for such challenging task.
%U https://aclanthology.org/2022.aacl-srw.9
%P 61-67
Markdown (Informal)
[An Empirical Study on Topic Preservation in Multi-Document Summarization](https://aclanthology.org/2022.aacl-srw.9) (Sim et al., AACL-IJCNLP 2022)
ACL
- Mong Yuan Sim, Wei Emma Zhang, and Congbo Ma. 2022. An Empirical Study on Topic Preservation in Multi-Document Summarization. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 61–67, Online. Association for Computational Linguistics.