Document summarization is a task to shorten texts into concise and informative summaries. This paper introduces a novel dataset designed for summarizing multiple scientific articles into a section of a survey. Our contributions are: (1) SurveySum, a new dataset addressing the gap in domain-specific summarization tools; (2) two specific pipelines to summarize scientific articles into a section of a survey; and (3) the evaluation of these pipelines using multiple metrics to compare their performance. Our results highlight the importance of high-quality retrieval stages and the impact of different configurations on the quality of generated summaries.
@article{arxiv.2408.16444,
title = {SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section},
author = {Leandro Carísio Fernandes and Gustavo Bartz Guedes and Thiago Soares Laitz and Thales Sales Almeida and Rodrigo Nogueira and Roberto Lotufo and Jayr Pereira},
journal= {arXiv preprint arXiv:2408.16444},
year = {2025}
}
Comments
15 pages, 6 figures, 1 table. Submitted to BRACIS 2024