@inproceedings{arumae-liu-2019-guiding,
title = "Guiding Extractive Summarization with Question-Answering Rewards",
author = "Arumae, Kristjan and
Liu, Fei",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1264",
doi = "10.18653/v1/N19-1264",
pages = "2566--2577",
abstract = "Highlighting while reading is a natural behavior for people to track salient content of a document. It would be desirable to teach an extractive summarizer to do the same. However, a major obstacle to the development of a supervised summarizer is the lack of ground-truth. Manual annotation of extraction units is cost-prohibitive, whereas acquiring labels by automatically aligning human abstracts and source documents can yield inferior results. In this paper we describe a novel framework to guide a supervised, extractive summarization system with question-answering rewards. We argue that quality summaries should serve as document surrogates to answer important questions, and such question-answer pairs can be conveniently obtained from human abstracts. The system learns to promote summaries that are informative, fluent, and perform competitively on question-answering. Our results compare favorably with those reported by strong summarization baselines as evaluated by automatic metrics and human assessors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arumae-liu-2019-guiding">
<titleInfo>
<title>Guiding Extractive Summarization with Question-Answering Rewards</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristjan</namePart>
<namePart type="family">Arumae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Highlighting while reading is a natural behavior for people to track salient content of a document. It would be desirable to teach an extractive summarizer to do the same. However, a major obstacle to the development of a supervised summarizer is the lack of ground-truth. Manual annotation of extraction units is cost-prohibitive, whereas acquiring labels by automatically aligning human abstracts and source documents can yield inferior results. In this paper we describe a novel framework to guide a supervised, extractive summarization system with question-answering rewards. We argue that quality summaries should serve as document surrogates to answer important questions, and such question-answer pairs can be conveniently obtained from human abstracts. The system learns to promote summaries that are informative, fluent, and perform competitively on question-answering. Our results compare favorably with those reported by strong summarization baselines as evaluated by automatic metrics and human assessors.</abstract>
<identifier type="citekey">arumae-liu-2019-guiding</identifier>
<identifier type="doi">10.18653/v1/N19-1264</identifier>
<location>
<url>https://aclanthology.org/N19-1264</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2566</start>
<end>2577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Guiding Extractive Summarization with Question-Answering Rewards
%A Arumae, Kristjan
%A Liu, Fei
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F arumae-liu-2019-guiding
%X Highlighting while reading is a natural behavior for people to track salient content of a document. It would be desirable to teach an extractive summarizer to do the same. However, a major obstacle to the development of a supervised summarizer is the lack of ground-truth. Manual annotation of extraction units is cost-prohibitive, whereas acquiring labels by automatically aligning human abstracts and source documents can yield inferior results. In this paper we describe a novel framework to guide a supervised, extractive summarization system with question-answering rewards. We argue that quality summaries should serve as document surrogates to answer important questions, and such question-answer pairs can be conveniently obtained from human abstracts. The system learns to promote summaries that are informative, fluent, and perform competitively on question-answering. Our results compare favorably with those reported by strong summarization baselines as evaluated by automatic metrics and human assessors.
%R 10.18653/v1/N19-1264
%U https://aclanthology.org/N19-1264
%U https://doi.org/10.18653/v1/N19-1264
%P 2566-2577
Markdown (Informal)
[Guiding Extractive Summarization with Question-Answering Rewards](https://aclanthology.org/N19-1264) (Arumae & Liu, NAACL 2019)
ACL
- Kristjan Arumae and Fei Liu. 2019. Guiding Extractive Summarization with Question-Answering Rewards. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2566–2577, Minneapolis, Minnesota. Association for Computational Linguistics.