@inproceedings{tsai-el-ghaoui-2020-sparse,
title = "Sparse Optimization for Unsupervised Extractive Summarization of Long Documents with the Frank-Wolfe Algorithm",
author = "Tsai, Alicia and
El Ghaoui, Laurent",
editor = "Moosavi, Nafise Sadat and
Fan, Angela and
Shwartz, Vered and
Glava{\v{s}}, Goran and
Joty, Shafiq and
Wang, Alex and
Wolf, Thomas",
booktitle = "Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sustainlp-1.8",
doi = "10.18653/v1/2020.sustainlp-1.8",
pages = "54--62",
abstract = "We address the problem of unsupervised extractive document summarization, especially for long documents. We model the unsupervised problem as a sparse auto-regression one and approximate the resulting combinatorial problem via a convex, norm-constrained problem. We solve it using a dedicated Frank-Wolfe algorithm. To generate a summary with k sentences, the algorithm only needs to execute approximately k iterations, making it very efficient for a long document. We evaluate our approach against two other unsupervised methods using both lexical (standard) ROUGE scores, as well as semantic (embedding-based) ones. Our method achieves better results with both datasets and works especially well when combined with embeddings for highly paraphrased summaries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsai-el-ghaoui-2020-sparse">
<titleInfo>
<title>Sparse Optimization for Unsupervised Extractive Summarization of Long Documents with the Frank-Wolfe Algorithm</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">El Ghaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nafise</namePart>
<namePart type="given">Sadat</namePart>
<namePart type="family">Moosavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wolf</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>We address the problem of unsupervised extractive document summarization, especially for long documents. We model the unsupervised problem as a sparse auto-regression one and approximate the resulting combinatorial problem via a convex, norm-constrained problem. We solve it using a dedicated Frank-Wolfe algorithm. To generate a summary with k sentences, the algorithm only needs to execute approximately k iterations, making it very efficient for a long document. We evaluate our approach against two other unsupervised methods using both lexical (standard) ROUGE scores, as well as semantic (embedding-based) ones. Our method achieves better results with both datasets and works especially well when combined with embeddings for highly paraphrased summaries.</abstract>
<identifier type="citekey">tsai-el-ghaoui-2020-sparse</identifier>
<identifier type="doi">10.18653/v1/2020.sustainlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2020.sustainlp-1.8</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>54</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sparse Optimization for Unsupervised Extractive Summarization of Long Documents with the Frank-Wolfe Algorithm
%A Tsai, Alicia
%A El Ghaoui, Laurent
%Y Moosavi, Nafise Sadat
%Y Fan, Angela
%Y Shwartz, Vered
%Y Glavaš, Goran
%Y Joty, Shafiq
%Y Wang, Alex
%Y Wolf, Thomas
%S Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F tsai-el-ghaoui-2020-sparse
%X We address the problem of unsupervised extractive document summarization, especially for long documents. We model the unsupervised problem as a sparse auto-regression one and approximate the resulting combinatorial problem via a convex, norm-constrained problem. We solve it using a dedicated Frank-Wolfe algorithm. To generate a summary with k sentences, the algorithm only needs to execute approximately k iterations, making it very efficient for a long document. We evaluate our approach against two other unsupervised methods using both lexical (standard) ROUGE scores, as well as semantic (embedding-based) ones. Our method achieves better results with both datasets and works especially well when combined with embeddings for highly paraphrased summaries.
%R 10.18653/v1/2020.sustainlp-1.8
%U https://aclanthology.org/2020.sustainlp-1.8
%U https://doi.org/10.18653/v1/2020.sustainlp-1.8
%P 54-62
Markdown (Informal)
[Sparse Optimization for Unsupervised Extractive Summarization of Long Documents with the Frank-Wolfe Algorithm](https://aclanthology.org/2020.sustainlp-1.8) (Tsai & El Ghaoui, sustainlp 2020)
ACL