Quality Enhancement of Abstractive Text Summaries with Content Selection

Abishek B. Rao; Shivani G. Aithal; Sanjay Singh

doi:10.1109/CICT56698.2022.9997835

Quality Enhancement of Abstractive Text Summaries with Content Selection

Abishek B. Rao, Shivani G. Aithal, Sanjay Singh

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

Abstract

Abstractive text summarization focuses on generating summaries by preserving the vital information from the source document. The content selector module proposed in this paper takes the source document's top n sentences and feeds them into the abstractive text summarization model to produce quality summaries. When combined with the content selector module, the abstractive text summarization model produces summaries that are semantically equivalent to the reference summaries. We use the ROUGE evaluation metric and human evaluation to assess the abstractive text summarization model's summaries with and without the content selector module. We found that the abstractive text summarization models using the content selector module provide summaries on par with those generated by humans.

Original language	English
Title of host publication	2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665473125
DOIs	https://doi.org/10.1109/CICT56698.2022.9997835
Publication status	Published - 2022
Event	6th IEEE Conference on Information and Communication Technology, CICT 2022 - Gwalior, India Duration: 18-11-2022 → 20-11-2022

Publication series

Name	2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022

Conference

Conference	6th IEEE Conference on Information and Communication Technology, CICT 2022
Country/Territory	India
City	Gwalior
Period	18-11-22 → 20-11-22

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Hardware and Architecture
Information Systems
Modelling and Simulation
Instrumentation

Access to Document

10.1109/CICT56698.2022.9997835

Cite this

Rao, A. B., Aithal, S. G., & Singh, S. (2022). Quality Enhancement of Abstractive Text Summaries with Content Selection. In 2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022 (2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CICT56698.2022.9997835

@inproceedings{f89076f0db8c4b8580a61f3de94157da,

title = "Quality Enhancement of Abstractive Text Summaries with Content Selection",

abstract = "Abstractive text summarization focuses on generating summaries by preserving the vital information from the source document. The content selector module proposed in this paper takes the source document's top n sentences and feeds them into the abstractive text summarization model to produce quality summaries. When combined with the content selector module, the abstractive text summarization model produces summaries that are semantically equivalent to the reference summaries. We use the ROUGE evaluation metric and human evaluation to assess the abstractive text summarization model's summaries with and without the content selector module. We found that the abstractive text summarization models using the content selector module provide summaries on par with those generated by humans.",

author = "Rao, {Abishek B.} and Aithal, {Shivani G.} and Sanjay Singh",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 6th IEEE Conference on Information and Communication Technology, CICT 2022 ; Conference date: 18-11-2022 Through 20-11-2022",

year = "2022",

doi = "10.1109/CICT56698.2022.9997835",

language = "English",

series = "2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022",

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

booktitle = "2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022",

address = "United States",

}

Rao, AB, Aithal, SG & Singh, S 2022, Quality Enhancement of Abstractive Text Summaries with Content Selection. in 2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022. 2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022, Institute of Electrical and Electronics Engineers Inc., 6th IEEE Conference on Information and Communication Technology, CICT 2022, Gwalior, India, 18-11-22. https://doi.org/10.1109/CICT56698.2022.9997835

Quality Enhancement of Abstractive Text Summaries with Content Selection. / Rao, Abishek B.; Aithal, Shivani G.; Singh, Sanjay.
2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022).

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

TY - GEN

T1 - Quality Enhancement of Abstractive Text Summaries with Content Selection

AU - Rao, Abishek B.

AU - Aithal, Shivani G.

AU - Singh, Sanjay

PY - 2022

Y1 - 2022

N2 - Abstractive text summarization focuses on generating summaries by preserving the vital information from the source document. The content selector module proposed in this paper takes the source document's top n sentences and feeds them into the abstractive text summarization model to produce quality summaries. When combined with the content selector module, the abstractive text summarization model produces summaries that are semantically equivalent to the reference summaries. We use the ROUGE evaluation metric and human evaluation to assess the abstractive text summarization model's summaries with and without the content selector module. We found that the abstractive text summarization models using the content selector module provide summaries on par with those generated by humans.

AB - Abstractive text summarization focuses on generating summaries by preserving the vital information from the source document. The content selector module proposed in this paper takes the source document's top n sentences and feeds them into the abstractive text summarization model to produce quality summaries. When combined with the content selector module, the abstractive text summarization model produces summaries that are semantically equivalent to the reference summaries. We use the ROUGE evaluation metric and human evaluation to assess the abstractive text summarization model's summaries with and without the content selector module. We found that the abstractive text summarization models using the content selector module provide summaries on par with those generated by humans.

UR - http://www.scopus.com/inward/record.url?scp=85146727202&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85146727202&partnerID=8YFLogxK

U2 - 10.1109/CICT56698.2022.9997835

DO - 10.1109/CICT56698.2022.9997835

M3 - Conference contribution

AN - SCOPUS:85146727202

T3 - 2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022

BT - 2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th IEEE Conference on Information and Communication Technology, CICT 2022

Y2 - 18 November 2022 through 20 November 2022

ER -

Quality Enhancement of Abstractive Text Summaries with Content Selection

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this