@inproceedings{shenouda-etal-2022-summvd,
title = "{S}umm{VD} : An efficient approach for unsupervised topic-based text summarization",
author = "Shenouda, Gabriel and
Bossard, Aur{\'e}lien and
Ayoub, Oussama and
Rodrigues, Christophe",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
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 (Volume 1: Long Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-main.38",
pages = "501--511",
abstract = "This paper introduces a new method, SummVD, for automatic unsupervised extractive summarization. This method is based on singular value decomposition, a linear method in the number of words, in order to reduce the dimensionality of word embeddings and propose a representation of words on a small number of dimensions, each representing a hidden topic. It also uses word clustering to reduce the vocabulary size. This representation, specific to one document, reduces the noise brought by several dimensions of the embeddings that are useless in a restricted context. It is followed by a linear sentence extraction heuristic. This makes SummVD an efficient method for text summarization. We evaluate SummVD using several corpora of different nature (news, scientific articles, social network). Our method outperforms in effectiveness recent extractive approaches. Moreover, SummVD requires low resources, in terms of data and computing power. So it can be run on long single documents such as scientific papers as much as large multi-document corpora and is fast enough to be used in live summarization systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shenouda-etal-2022-summvd">
<titleInfo>
<title>SummVD : An efficient approach for unsupervised topic-based text summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Shenouda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélien</namePart>
<namePart type="family">Bossard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oussama</namePart>
<namePart type="family">Ayoub</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Rodrigues</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 (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a new method, SummVD, for automatic unsupervised extractive summarization. This method is based on singular value decomposition, a linear method in the number of words, in order to reduce the dimensionality of word embeddings and propose a representation of words on a small number of dimensions, each representing a hidden topic. It also uses word clustering to reduce the vocabulary size. This representation, specific to one document, reduces the noise brought by several dimensions of the embeddings that are useless in a restricted context. It is followed by a linear sentence extraction heuristic. This makes SummVD an efficient method for text summarization. We evaluate SummVD using several corpora of different nature (news, scientific articles, social network). Our method outperforms in effectiveness recent extractive approaches. Moreover, SummVD requires low resources, in terms of data and computing power. So it can be run on long single documents such as scientific papers as much as large multi-document corpora and is fast enough to be used in live summarization systems.</abstract>
<identifier type="citekey">shenouda-etal-2022-summvd</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-main.38</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>501</start>
<end>511</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SummVD : An efficient approach for unsupervised topic-based text summarization
%A Shenouda, Gabriel
%A Bossard, Aurélien
%A Ayoub, Oussama
%A Rodrigues, Christophe
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%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 (Volume 1: Long Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F shenouda-etal-2022-summvd
%X This paper introduces a new method, SummVD, for automatic unsupervised extractive summarization. This method is based on singular value decomposition, a linear method in the number of words, in order to reduce the dimensionality of word embeddings and propose a representation of words on a small number of dimensions, each representing a hidden topic. It also uses word clustering to reduce the vocabulary size. This representation, specific to one document, reduces the noise brought by several dimensions of the embeddings that are useless in a restricted context. It is followed by a linear sentence extraction heuristic. This makes SummVD an efficient method for text summarization. We evaluate SummVD using several corpora of different nature (news, scientific articles, social network). Our method outperforms in effectiveness recent extractive approaches. Moreover, SummVD requires low resources, in terms of data and computing power. So it can be run on long single documents such as scientific papers as much as large multi-document corpora and is fast enough to be used in live summarization systems.
%U https://aclanthology.org/2022.aacl-main.38
%P 501-511
Markdown (Informal)
[SummVD : An efficient approach for unsupervised topic-based text summarization](https://aclanthology.org/2022.aacl-main.38) (Shenouda et al., AACL-IJCNLP 2022)
ACL
- Gabriel Shenouda, Aurélien Bossard, Oussama Ayoub, and Christophe Rodrigues. 2022. SummVD : An efficient approach for unsupervised topic-based text 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 (Volume 1: Long Papers), pages 501–511, Online only. Association for Computational Linguistics.