English

Citance-Contextualized Summarization of Scientific Papers

Computation and Language 2023-11-14 v3

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\textbf{Webis-Context-SciSumm-2023}, a new dataset containing 540K~computer science papers and 4.6M~citances therein.

Keywords

Cite

@article{arxiv.2311.02408,
  title  = {Citance-Contextualized Summarization of Scientific Papers},
  author = {Shahbaz Syed and Ahmad Dawar Hakimi and Khalid Al-Khatib and Martin Potthast},
  journal= {arXiv preprint arXiv:2311.02408},
  year   = {2023}
}

Comments

Accepted at EMNLP 2023 Findings

R2 v1 2026-06-28T13:11:34.410Z