Leveraging peer-review aspects for extractive and abstractive summarization of scientific articles
Open Access
- 18 October 2024
- journal article
- research article
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 19 (3) , 537-550
Abstract
This research introduces an innovative framework that supports the peer-review process by automatically extracting the following four key aspects of a scientific paper: contribution, motivation, claims, and claims support. Leveraging these extracted aspects, we generate extractive and abstractive summaries of scientific papers. Additionally, we provide a benchmarking corpus containing 1000 aspect-related sentences extracted from 40 scientific articles, which can serve as a valuable resource for evaluating various aspect extraction methods. Experimental findings reveal that our automated aspect extraction system successfully identifies between 86 and 92% of sentences related to each aspect with precision ranging from 84 to 94%. The aspect-based extractive summaries outperformed the original paper abstracts in terms of the Rouge scores as well as in Relevance, Consistency, Fluency, and Coherence dimensions. Furthermore, our study demonstrates that by prompting the LLMs using the paper itself along with the extracted aspects, the LLM-generated summaries exhibit superior performance compared to prompting with either the paper or the abstract only.Keywords
Funding Information
- Ben-Gurion University
This publication has 37 references indexed in Scilit:
- Leveraging BERT for extractive text summarization on federal police documentsKnowledge and Information Systems, 2023
- An abstractive summary generation system for customer reviews and news article using deep learningJournal of Ambient Intelligence and Humanized Computing, 2020
- Recent advances in scaling‐down sampling methods in machine learningWIREs Computational Statistics, 2017
- Section mixture models for scientific document summarizationInternational Journal on Digital Libraries, 2017
- Scientific document summarization via citation contextualization and scientific discourseInternational Journal on Digital Libraries, 2017
- Your Paper has been Accepted, Rejected, or Whatever: Automatic Generation of Scientific Paper Reviews2016
- Aspect extraction in sentiment analysis: comparative analysis and surveyArtificial Intelligence Review, 2016
- Wilcoxon Signed‐Rank Test2008
- Blind men and elephants: What do citation summaries tell us about a research article?Journal of the American Society for Information Science and Technology, 2007
- Extracting Product Features and Opinions from Reviews2007