ContributionSum: Generating Disentangled Contributions for Scientific Papers

Meng Huan Liu, An Zi Yen, Hen Hsen Huang, Hsin Hsi Chen

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

Contributions are essentially the core of every scientific research, highlighting their key values to the academic community. Systems that are capable of identifying the contributions from scientific papers precisely and organizing them into well-structured summaries can facilitate both text processing and human comprehension. In this paper, we present ContributionSum, a dataset consisting of 24K computer science papers with contributions explicitly listed by the authors, which are further classified into different contribution types based on a newly-proposed annotation scheme. In addition, we study the task of generating disentangled contributions that summarize the values of scientific papers into key points. We propose a fine-grained post-training strategy tailored to our task and leverage salient information of different contribution types in the papers. To assess the coherency and coverage of each contribution aspect, we perform summary-level and contribution-level evaluations for our task. Experimental results show that our method improves upon mainstream baselines.

原文English
主出版物標題CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
發行者Association for Computing Machinery
頁面5351-5355
頁數5
ISBN(電子)9798400701245
DOIs
出版狀態Published - 21 10月 2023
事件32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 - Birmingham, 英國
持續時間: 21 10月 202325 10月 2023

出版系列

名字International Conference on Information and Knowledge Management, Proceedings

Conference

Conference32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
國家/地區英國
城市Birmingham
期間21/10/2325/10/23

指紋

深入研究「ContributionSum: Generating Disentangled Contributions for Scientific Papers」主題。共同形成了獨特的指紋。

引用此