Citance-Contextualized Summarization of Scientific Papers
Shahbaz Syed, Ahmad Dawar Hakimi, Khalid Al Khatib, Martin Potthast
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.
BibTeX
@inproceedings{
syed2023citancecontextualized,
title={Citance-Contextualized Summarization of Scientific Papers},
author={Shahbaz Syed and Ahmad Dawar Hakimi and Khalid Al Khatib and Martin Potthast},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=T9jJsFUGtI}
}