Automating news summarization with sentence vectors offset

Mauricio Steinert; Roger Granada; Joao Paulo Aires; Felipe Meneguzzi

doi:10.1109/BRACIS.2019.00027

Automating news summarization with sentence vectors offset

Mauricio Steinert, Roger Granada, Joao Paulo Aires, Felipe Meneguzzi

Computing Science

Pontifícia Universidade Católica do Rio Grande do Sul

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

Abstract

Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.

Original language	English
Title of host publication	Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	102-107
Number of pages	6
ISBN (Electronic)	9781728142531
DOIs	https://doi.org/10.1109/BRACIS.2019.00027
Publication status	Published - Oct 2019
Event	8th Brazilian Conference on Intelligent Systems, BRACIS 2019 - Salvador, Bahia, Brazil Duration: 15 Oct 2019 → 18 Oct 2019

Publication series

Name	Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019

Conference

Conference	8th Brazilian Conference on Intelligent Systems, BRACIS 2019
Country/Territory	Brazil
City	Salvador, Bahia
Period	15/10/19 → 18/10/19

Bibliographical note

Funding Information:
Acknowledgements: This study was financed in part by the Coordenac¸ão de Aperfeic¸oamento de Pessoal de Nível Superior (CAPES) and Fundac¸ão de Amparo à Pesquisa do Estado do Rio Grande do Sul (FAPERGS) agreement (DOCFIX 04/2018). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.

Publisher Copyright:
© 2019 IEEE.

Keywords

Automatic text summarization
Information retrieval
Natural language processing
Word embedding

Access to Document

10.1109/BRACIS.2019.00027

Cite this

Steinert, M., Granada, R., Aires, J. P., & Meneguzzi, F. (2019). Automating news summarization with sentence vectors offset. In Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019 (pp. 102-107). Article 8924017 (Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BRACIS.2019.00027

Automating news summarization with sentence vectors offset. / Steinert, Mauricio; Granada, Roger; Aires, Joao Paulo et al.
Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 102-107 8924017 (Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019).

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

Steinert, M, Granada, R, Aires, JP & Meneguzzi, F 2019, Automating news summarization with sentence vectors offset. in Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019., 8924017, Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 102-107, 8th Brazilian Conference on Intelligent Systems, BRACIS 2019, Salvador, Bahia, Brazil, 15/10/19. https://doi.org/10.1109/BRACIS.2019.00027

Steinert M, Granada R, Aires JP, Meneguzzi F. Automating news summarization with sentence vectors offset. In Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 102-107. 8924017. (Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019). doi: 10.1109/BRACIS.2019.00027

@inproceedings{834a339a236b4029ab584257c18e075b,

title = "Automating news summarization with sentence vectors offset",

abstract = "Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.",

keywords = "Automatic text summarization, Information retrieval, Natural language processing, Word embedding",

author = "Mauricio Steinert and Roger Granada and Aires, {Joao Paulo} and Felipe Meneguzzi",

note = "Funding Information: Acknowledgements: This study was financed in part by the Coordenac¸{\~a}o de Aperfeic¸oamento de Pessoal de N{\'i}vel Superior (CAPES) and Fundac¸{\~a}o de Amparo {\`a} Pesquisa do Estado do Rio Grande do Sul (FAPERGS) agreement (DOCFIX 04/2018). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. Publisher Copyright: {\textcopyright} 2019 IEEE.; 8th Brazilian Conference on Intelligent Systems, BRACIS 2019 ; Conference date: 15-10-2019 Through 18-10-2019",

year = "2019",

month = oct,

doi = "10.1109/BRACIS.2019.00027",

language = "English",

series = "Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "102--107",

booktitle = "Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019",

address = "United States",

}

TY - GEN

T1 - Automating news summarization with sentence vectors offset

AU - Steinert, Mauricio

AU - Granada, Roger

AU - Aires, Joao Paulo

AU - Meneguzzi, Felipe

N1 - Funding Information: Acknowledgements: This study was financed in part by the Coordenac¸ão de Aperfeic¸oamento de Pessoal de Nível Superior (CAPES) and Fundac¸ão de Amparo à Pesquisa do Estado do Rio Grande do Sul (FAPERGS) agreement (DOCFIX 04/2018). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. Publisher Copyright: © 2019 IEEE.

PY - 2019/10

Y1 - 2019/10

N2 - Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.

AB - Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.

KW - Automatic text summarization

KW - Information retrieval

KW - Natural language processing

KW - Word embedding

UR - http://www.scopus.com/inward/record.url?scp=85077082628&partnerID=8YFLogxK

U2 - 10.1109/BRACIS.2019.00027

DO - 10.1109/BRACIS.2019.00027

M3 - Published conference contribution

AN - SCOPUS:85077082628

T3 - Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019

SP - 102

EP - 107

BT - Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th Brazilian Conference on Intelligent Systems, BRACIS 2019

Y2 - 15 October 2019 through 18 October 2019

ER -

Automating news summarization with sentence vectors offset

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this