Generating Summaries with Topic Templates and Structured Convolutional Decoders

Laura Perez-Beltrachini; Yang Liu; Mirella Lapata

doi:10.18653/v1/P19-1504

Generating Summaries with Topic Templates and Structured Convolutional Decoders

Laura Perez-Beltrachini, Yang Liu, Mirella Lapata

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

Abstract

Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with existing sequential decoders on three data sets representing different domains. Automatic and human evaluation demonstrate that our summaries have better content coverage.

Original language	English
Title of host publication	Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Place of Publication	Florence, Italy
Publisher	Association for Computational Linguistics
Pages	5107-5116
Number of pages	10
DOIs	https://doi.org/10.18653/v1/P19-1504
Publication status	Published - 31 Jul 2019
Event	57th Annual Meeting of the Association for Computational Linguistics - Fortezza da Basso, Florence, Italy Duration: 28 Jul 2019 → 2 Aug 2019 Conference number: 57 http://www.acl2019.org/EN/index.xhtml

Conference

Conference	57th Annual Meeting of the Association for Computational Linguistics
Abbreviated title	ACL 2019
Country/Territory	Italy
City	Florence
Period	28/07/19 → 2/08/19
Internet address	http://www.acl2019.org/EN/index.xhtml

Access to Document

10.18653/v1/P19-1504Licence: Creative Commons: Attribution (CC-BY)

Generating Summaries with_PEREZ_DOA130519_AFVAccepted author manuscript, 262 KBLicence: Creative Commons: Attribution (CC-BY)
Generating Summaries with_PEREZ_DOA130519_VOR_CC-BYFinal published version, 359 KBLicence: Creative Commons: Attribution (CC-BY)

https://www.aclweb.org/anthology/P19-1504Licence: Creative Commons: Attribution (CC-BY)

TransModal: Translating from Multiple Modalities into Text
Lapata, M. (Principal Investigator)
EU government bodies
1/09/16 → 31/08/22
Project: Research

Cite this

@inproceedings{742224d81d394199ba536f2f0de0742f,

title = "Generating Summaries with Topic Templates and Structured Convolutional Decoders",

abstract = "Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with existing sequential decoders on three data sets representing different domains. Automatic and human evaluation demonstrate that our summaries have better content coverage.",

author = "Laura Perez-Beltrachini and Yang Liu and Mirella Lapata",

year = "2019",

month = jul,

day = "31",

doi = "10.18653/v1/P19-1504",

language = "English",

pages = "5107--5116",

booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

url = "http://www.acl2019.org/EN/index.xhtml",

}

Perez-Beltrachini, L, Liu, Y & Lapata, M 2019, Generating Summaries with Topic Templates and Structured Convolutional Decoders. in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Florence, Italy, pp. 5107-5116, 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 28/07/19. https://doi.org/10.18653/v1/P19-1504

Generating Summaries with Topic Templates and Structured Convolutional Decoders. / Perez-Beltrachini, Laura; Liu, Yang; Lapata, Mirella.
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy: Association for Computational Linguistics, 2019. p. 5107-5116.

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

TY - GEN

T1 - Generating Summaries with Topic Templates and Structured Convolutional Decoders

AU - Perez-Beltrachini, Laura

AU - Liu, Yang

AU - Lapata, Mirella

N1 - Conference code: 57

PY - 2019/7/31

Y1 - 2019/7/31

N2 - Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with existing sequential decoders on three data sets representing different domains. Automatic and human evaluation demonstrate that our summaries have better content coverage.

AB - Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with existing sequential decoders on three data sets representing different domains. Automatic and human evaluation demonstrate that our summaries have better content coverage.

U2 - 10.18653/v1/P19-1504

DO - 10.18653/v1/P19-1504

M3 - Conference contribution

SP - 5107

EP - 5116

BT - Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics

CY - Florence, Italy

T2 - 57th Annual Meeting of the Association for Computational Linguistics

Y2 - 28 July 2019 through 2 August 2019

ER -

Generating Summaries with Topic Templates and Structured Convolutional Decoders

Abstract

Conference

Access to Document

Fingerprint

Projects

TransModal: Translating from Multiple Modalities into Text

Cite this