Abstractive sentence summarization with attentive recurrent neural networks

Sumit Chopra; Michael Auli; Alexander M. Rush

doi:10.18653/v1/n16-1012

Abstractive sentence summarization with attentive recurrent neural networks

Sumit Chopra, Michael Auli, Alexander M. Rush

Computer Science

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

Abstract

Abstractive Sentence Summarization generates a shorter version of a given sentence while attempting to preserve its meaning. We introduce a conditional recurrent neural network (RNN) which generates a summary of an input sentence. The conditioning is provided by a novel convolutional attention-based encoder which ensures that the decoder focuses on the appropriate input words at each step of generation. Our model relies only on learned features and is easy to train in an end-to-end fashion on large data sets. Our experiments show that the model significantly outperforms the recently proposed state-of-the-art method on the Gigaword corpus while performing competitively on the DUC-2004 shared task.

Original language	English (US)
Title of host publication	2016 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	93-98
Number of pages	6
ISBN (Electronic)	9781941643914
DOIs	https://doi.org/10.18653/v1/n16-1012
State	Published - 2016
Event	15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - San Diego, United States Duration: Jun 12 2016 → Jun 17 2016

Publication series

Name	2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference

Other

Other	15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016
Country/Territory	United States
City	San Diego
Period	6/12/16 → 6/17/16

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Access to Document

10.18653/v1/n16-1012

Cite this

Chopra, S., Auli, M., & Rush, A. M. (2016). Abstractive sentence summarization with attentive recurrent neural networks. In 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference (pp. 93-98). (2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/n16-1012

Abstractive sentence summarization with attentive recurrent neural networks. / Chopra, Sumit; Auli, Michael; Rush, Alexander M.
2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL), 2016. p. 93-98 (2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference).

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

Chopra, S, Auli, M & Rush, AM 2016, Abstractive sentence summarization with attentive recurrent neural networks. in 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 93-98, 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016, San Diego, United States, 6/12/16. https://doi.org/10.18653/v1/n16-1012

Chopra S, Auli M, Rush AM. Abstractive sentence summarization with attentive recurrent neural networks. In 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL). 2016. p. 93-98. (2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference). doi: 10.18653/v1/n16-1012

Chopra, Sumit ; Auli, Michael ; Rush, Alexander M. / Abstractive sentence summarization with attentive recurrent neural networks. 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL), 2016. pp. 93-98 (2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference).

@inproceedings{815285ecfc1d411f943513402655c1f0,

title = "Abstractive sentence summarization with attentive recurrent neural networks",

abstract = "Abstractive Sentence Summarization generates a shorter version of a given sentence while attempting to preserve its meaning. We introduce a conditional recurrent neural network (RNN) which generates a summary of an input sentence. The conditioning is provided by a novel convolutional attention-based encoder which ensures that the decoder focuses on the appropriate input words at each step of generation. Our model relies only on learned features and is easy to train in an end-to-end fashion on large data sets. Our experiments show that the model significantly outperforms the recently proposed state-of-the-art method on the Gigaword corpus while performing competitively on the DUC-2004 shared task.",

author = "Sumit Chopra and Michael Auli and Rush, {Alexander M.}",

note = "Publisher Copyright: {\textcopyright}2016 Association for Computational Linguistics.; 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 ; Conference date: 12-06-2016 Through 17-06-2016",

year = "2016",

doi = "10.18653/v1/n16-1012",

language = "English (US)",

series = "2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference",

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

pages = "93--98",

booktitle = "2016 Conference of the North American Chapter of the Association for Computational Linguistics",

}

TY - GEN

T1 - Abstractive sentence summarization with attentive recurrent neural networks

AU - Chopra, Sumit

AU - Auli, Michael

AU - Rush, Alexander M.

PY - 2016

Y1 - 2016

N2 - Abstractive Sentence Summarization generates a shorter version of a given sentence while attempting to preserve its meaning. We introduce a conditional recurrent neural network (RNN) which generates a summary of an input sentence. The conditioning is provided by a novel convolutional attention-based encoder which ensures that the decoder focuses on the appropriate input words at each step of generation. Our model relies only on learned features and is easy to train in an end-to-end fashion on large data sets. Our experiments show that the model significantly outperforms the recently proposed state-of-the-art method on the Gigaword corpus while performing competitively on the DUC-2004 shared task.

AB - Abstractive Sentence Summarization generates a shorter version of a given sentence while attempting to preserve its meaning. We introduce a conditional recurrent neural network (RNN) which generates a summary of an input sentence. The conditioning is provided by a novel convolutional attention-based encoder which ensures that the decoder focuses on the appropriate input words at each step of generation. Our model relies only on learned features and is easy to train in an end-to-end fashion on large data sets. Our experiments show that the model significantly outperforms the recently proposed state-of-the-art method on the Gigaword corpus while performing competitively on the DUC-2004 shared task.

UR - http://www.scopus.com/inward/record.url?scp=84994154380&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994154380&partnerID=8YFLogxK

U2 - 10.18653/v1/n16-1012

DO - 10.18653/v1/n16-1012

M3 - Conference contribution

AN - SCOPUS:84994154380

T3 - 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference

SP - 93

EP - 98

BT - 2016 Conference of the North American Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

T2 - 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016

Y2 - 12 June 2016 through 17 June 2016

ER -

Abstractive sentence summarization with attentive recurrent neural networks

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this