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 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.
%0 Conference Paper
%1 syed-etal-2023-citance
%A Syed, Shahbaz
%A Hakimi, Ahmad
%A Al-Khatib, Khalid
%A Potthast, Martin
%B Findings of the Association for Computational Linguistics: EMNLP 2023
%C Singapore
%D 2023
%E Bouamor, Houda
%E Pino, Juan
%E Bali, Kalika
%I Association for Computational Linguistics
%K imported
%P 8551--8568
%R 10.18653/v1/2023.findings-emnlp.573
%T Citance-Contextualized Summarization of Scientific Papers
%U https://aclanthology.org/2023.findings-emnlp.573
%X 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 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.
@inproceedings{syed-etal-2023-citance,
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 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.},
added-at = {2024-11-19T15:34:37.000+0100},
address = {Singapore},
author = {Syed, Shahbaz and Hakimi, Ahmad and Al-Khatib, Khalid and Potthast, Martin},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2858bf64b5b67d009120a93abd866bcf2/scadsfct},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023},
doi = {10.18653/v1/2023.findings-emnlp.573},
editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika},
interhash = {42a930adbee90f0fe33aca570d73d2ec},
intrahash = {858bf64b5b67d009120a93abd866bcf2},
keywords = {imported},
month = dec,
pages = {8551--8568},
publisher = {Association for Computational Linguistics},
timestamp = {2024-11-19T15:34:37.000+0100},
title = {Citance-Contextualized Summarization of Scientific Papers},
url = {https://aclanthology.org/2023.findings-emnlp.573},
year = 2023
}
