Citance-Contextualized Summarization of Scientific Papers
Submission Type: Regular Long Paper
Submission Track: Summarization
Submission Track 2: NLP Applications
Keywords: Summarization, Scholarly Document Processing, Scientific Papers, Large Language Models
TL;DR: We propose contextualized summarization of scientific papers grounded in the citation contexts.
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.
Submission Number: 4057
Loading