SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fernandes, Leandro Carísio, Guedes, Gustavo Bartz, Laitz, Thiago Soares, Almeida, Thales Sales, Nogueira, Rodrigo, Lotufo, Roberto, Pereira, Jayr
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910876334817280
author Fernandes, Leandro Carísio
Guedes, Gustavo Bartz
Laitz, Thiago Soares
Almeida, Thales Sales
Nogueira, Rodrigo
Lotufo, Roberto
Pereira, Jayr
author_facet Fernandes, Leandro Carísio
Guedes, Gustavo Bartz
Laitz, Thiago Soares
Almeida, Thales Sales
Nogueira, Rodrigo
Lotufo, Roberto
Pereira, Jayr
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16444
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section
Fernandes, Leandro Carísio
Guedes, Gustavo Bartz
Laitz, Thiago Soares
Almeida, Thales Sales
Nogueira, Rodrigo
Lotufo, Roberto
Pereira, Jayr
Computation and Language
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.
title SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section
topic Computation and Language
url https://arxiv.org/abs/2408.16444