Ranking Sentences for Extractive Summarization with Reinforcement Learning

Shashi Narayan; Shay B. Cohen; Mirella Lapata

doi:10.18653/v1/N18-1158

Ranking Sentences for Extractive Summarization with Reinforcement Learning

Shashi Narayan, Shay B. Cohen, Mirella Lapata

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. We use our algorithm to train a neural summarization model on the CNN and DailyMail datasets and demonstrate experimentally that it outperforms state-of-the-art extractive and abstractive systems when evaluated automatically and by humans.

Original language	English
Title of host publication	Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Place of Publication	New Orleans, Louisiana
Publisher	Association for Computational Linguistics (ACL)
Pages	1747-1759
Number of pages	13
ISBN (Print)	978-1-948087-27-8
DOIs	https://doi.org/10.18653/v1/N18-1158
Publication status	Published - 6 Jun 2018
Event	16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Hyatt Regency New Orleans Hotel, New Orleans, United States Duration: 1 Jun 2018 → 6 Jun 2018 http://naacl2018.org/

Conference

Conference	16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Abbreviated title	NAACL HLT 2018
Country/Territory	United States
City	New Orleans
Period	1/06/18 → 6/06/18
Internet address	http://naacl2018.org/

Access to Document

10.18653/v1/N18-1158Licence: Creative Commons: Attribution (CC-BY)

reinforced-extsumAccepted author manuscript, 176 KB

http://aclweb.org/anthology/N18-1158 Licence: Creative Commons: Attribution (CC-BY)

Cite this

Narayan, S., Cohen, S. B., & Lapata, M. (2018). Ranking Sentences for Extractive Summarization with Reinforcement Learning. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) (pp. 1747-1759). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/N18-1158

Narayan, Shashi ; Cohen, Shay B. ; Lapata, Mirella. / Ranking Sentences for Extractive Summarization with Reinforcement Learning. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). New Orleans, Louisiana : Association for Computational Linguistics (ACL), 2018. pp. 1747-1759

@inproceedings{7cf77471c6b04e2687310f785b811ad0,

title = "Ranking Sentences for Extractive Summarization with Reinforcement Learning",

abstract = "Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. We use our algorithm to train a neural summarization model on the CNN and DailyMail datasets and demonstrate experimentally that it outperforms state-of-the-art extractive and abstractive systems when evaluated automatically and by humans. ",

author = "Shashi Narayan and Cohen, {Shay B.} and Mirella Lapata",

year = "2018",

month = jun,

day = "6",

doi = "10.18653/v1/N18-1158",

language = "English",

isbn = "978-1-948087-27-8",

pages = "1747--1759",

booktitle = "Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",

publisher = "Association for Computational Linguistics (ACL)",

note = "16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 01-06-2018 Through 06-06-2018",

url = "http://naacl2018.org/",

}

Narayan, S, Cohen, SB & Lapata, M 2018, Ranking Sentences for Extractive Summarization with Reinforcement Learning. in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Association for Computational Linguistics (ACL), New Orleans, Louisiana , pp. 1747-1759, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, United States, 1/06/18. https://doi.org/10.18653/v1/N18-1158

Ranking Sentences for Extractive Summarization with Reinforcement Learning. / Narayan, Shashi; Cohen, Shay B.; Lapata, Mirella.
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). New Orleans, Louisiana : Association for Computational Linguistics (ACL), 2018. p. 1747-1759.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Ranking Sentences for Extractive Summarization with Reinforcement Learning

AU - Narayan, Shashi

AU - Cohen, Shay B.

AU - Lapata, Mirella

PY - 2018/6/6

Y1 - 2018/6/6

N2 - Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. We use our algorithm to train a neural summarization model on the CNN and DailyMail datasets and demonstrate experimentally that it outperforms state-of-the-art extractive and abstractive systems when evaluated automatically and by humans.

AB - Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. We use our algorithm to train a neural summarization model on the CNN and DailyMail datasets and demonstrate experimentally that it outperforms state-of-the-art extractive and abstractive systems when evaluated automatically and by humans.

UR - http://naacl2018.org/

U2 - 10.18653/v1/N18-1158

DO - 10.18653/v1/N18-1158

M3 - Conference contribution

SN - 978-1-948087-27-8

SP - 1747

EP - 1759

BT - Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

PB - Association for Computational Linguistics (ACL)

CY - New Orleans, Louisiana

T2 - 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Y2 - 1 June 2018 through 6 June 2018

ER -

Narayan S, Cohen SB , Lapata M. Ranking Sentences for Extractive Summarization with Reinforcement Learning. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). New Orleans, Louisiana : Association for Computational Linguistics (ACL). 2018. p. 1747-1759 doi: 10.18653/v1/N18-1158

Ranking Sentences for Extractive Summarization with Reinforcement Learning

Abstract

Conference

Access to Document

Other files and links

Fingerprint

TransModal: Translating from Multiple Modalities into Text

SUMMA - Scalable Understanding of Mulitingual Media

Shay Cohen

Cite this

Ranking Sentences for Extractive Summarization with Reinforcement Learning

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Projects

TransModal: Translating from Multiple Modalities into Text

SUMMA - Scalable Understanding of Mulitingual Media

Profiles

Shay Cohen

Cite this