Citance-Contextualized Summarization of Scientific Papers

Shahbaz Syed; Ahmad Dawar Hakimi; Khalid Al-Khatib; Martin Potthast

doi:10.18653/v1/2023.findings-emnlp.573

Citance-Contextualized Summarization of Scientific Papers

Shahbaz Syed^*, Ahmad Dawar Hakimi, Khalid Al-Khatib, Martin Potthast

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

56 Downloads (Pure)

Abstract

Current approaches to automatic summarization of scientific papers generate informative summaries in the form of abstracts. However, abstracts are not intended to show the relationship between a paper and the references cited in it. We propose a new contextualized summarization approach that can generate an informative summary conditioned on a given sentence containing the citation of a reference (a so-called “citance”). This summary outlines the content of the cited paper relevant to the citation location. Thus, our approach extracts and models the citances of a paper, retrieves relevant passages from cited papers, and generates abstractive summaries tailored to each citance. We evaluate our approach using WEBIS-CONTEXT-SCISUMM-2023, a new dataset containing 540K computer science papers and 4.6M citances therein.

Original language	English
Title of host publication	Findings of the Association for Computational Linguistics
Subtitle of host publication	EMNLP 2023
Editors	Houda Bouamor, Juan Pino, Kalika Bali
Publisher	Association for Computational Linguistics (ACL)
Pages	8551-8568
Number of pages	18
ISBN (Electronic)	9798891760615
DOIs	https://doi.org/10.18653/v1/2023.findings-emnlp.573
Publication status	Published - 2023
Event	2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023) - Singapore, Singapore Duration: 6-Dec-2023 → 10-Dec-2023

Conference

Conference	2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)
Country/Territory	Singapore
City	Singapore
Period	06/12/2023 → 10/12/2023

Access to Document

10.18653/v1/2023.findings-emnlp.573Licence: CC BY

Citance-Contextualized Summarization of Scientific PapersFinal publisher's version, 601 KBLicence: CC BY

Handle.net

Persistent link

Cite this

@inproceedings{b8f4faf8904742729067668a2a6524bd,

title = "Citance-Contextualized Summarization of Scientific Papers",

abstract = "Current approaches to automatic summarization of scientific papers generate informative summaries in the form of abstracts. However, abstracts are not intended to show the relationship between a paper and the references cited in it. We propose a new contextualized summarization approach that can generate an informative summary conditioned on a given sentence containing the citation of a reference (a so-called “citance”). This summary outlines the content of the cited paper relevant to the citation location. Thus, our approach extracts and models the citances of a paper, retrieves relevant passages from cited papers, and generates abstractive summaries tailored to each citance. We evaluate our approach using WEBIS-CONTEXT-SCISUMM-2023, a new dataset containing 540K computer science papers and 4.6M citances therein.",

author = "Shahbaz Syed and Hakimi, {Ahmad Dawar} and Khalid Al-Khatib and Martin Potthast",

note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023) ; Conference date: 06-12-2023 Through 10-12-2023",

year = "2023",

doi = "10.18653/v1/2023.findings-emnlp.573",

language = "English",

pages = "8551--8568",

editor = "Houda Bouamor and Juan Pino and Kalika Bali",

booktitle = "Findings of the Association for Computational Linguistics",

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

}

Syed, S, Hakimi, AD, Al-Khatib, K & Potthast, M 2023, Citance-Contextualized Summarization of Scientific Papers. in H Bouamor, J Pino & K Bali (eds), Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics (ACL), pp. 8551-8568, 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore, Singapore, 06/12/2023. https://doi.org/10.18653/v1/2023.findings-emnlp.573

Citance-Contextualized Summarization of Scientific Papers. / Syed, Shahbaz; Hakimi, Ahmad Dawar; Al-Khatib, Khalid et al.
Findings of the Association for Computational Linguistics: EMNLP 2023. ed. / Houda Bouamor; Juan Pino; Kalika Bali. Association for Computational Linguistics (ACL), 2023. p. 8551-8568.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Citance-Contextualized Summarization of Scientific Papers

AU - Syed, Shahbaz

AU - Hakimi, Ahmad Dawar

AU - Al-Khatib, Khalid

AU - Potthast, Martin

PY - 2023

Y1 - 2023

N2 - Current approaches to automatic summarization of scientific papers generate informative summaries in the form of abstracts. However, abstracts are not intended to show the relationship between a paper and the references cited in it. We propose a new contextualized summarization approach that can generate an informative summary conditioned on a given sentence containing the citation of a reference (a so-called “citance”). This summary outlines the content of the cited paper relevant to the citation location. Thus, our approach extracts and models the citances of a paper, retrieves relevant passages from cited papers, and generates abstractive summaries tailored to each citance. We evaluate our approach using WEBIS-CONTEXT-SCISUMM-2023, a new dataset containing 540K computer science papers and 4.6M citances therein.

AB - Current approaches to automatic summarization of scientific papers generate informative summaries in the form of abstracts. However, abstracts are not intended to show the relationship between a paper and the references cited in it. We propose a new contextualized summarization approach that can generate an informative summary conditioned on a given sentence containing the citation of a reference (a so-called “citance”). This summary outlines the content of the cited paper relevant to the citation location. Thus, our approach extracts and models the citances of a paper, retrieves relevant passages from cited papers, and generates abstractive summaries tailored to each citance. We evaluate our approach using WEBIS-CONTEXT-SCISUMM-2023, a new dataset containing 540K computer science papers and 4.6M citances therein.

UR - http://www.scopus.com/inward/record.url?scp=85183300839&partnerID=8YFLogxK

U2 - 10.18653/v1/2023.findings-emnlp.573

DO - 10.18653/v1/2023.findings-emnlp.573

M3 - Conference contribution

AN - SCOPUS:85183300839

SP - 8551

EP - 8568

BT - Findings of the Association for Computational Linguistics

A2 - Bouamor, Houda

A2 - Pino, Juan

A2 - Bali, Kalika

PB - Association for Computational Linguistics (ACL)

T2 - 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)

Y2 - 6 December 2023 through 10 December 2023

ER -

Citance-Contextualized Summarization of Scientific Papers

Abstract

Conference

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this