An Interactive Approach for Query-Based Multi-Document Scientific Text Summarization

The overwhelming volume of scientific documents necessitates automatic summarization to assist researchers in efficiently finding relevant data, making informed decisions, and retrieving appropriate answers to their queries. Query-based automatic summarization is to provide a textual summary related...

Full description

Saved in:
Bibliographic Details
Published inInternational eConference on Computer and Knowledge Engineering (Online) pp. 230 - 234
Main Authors Nejati, Mohammadsadra, Ahmadi, Abbas, Mohebi, Azadeh
Format Conference Proceeding
LanguageEnglish
Published IEEE 19.11.2024
Subjects
Coherence
Computational modeling
Computer architecture
Filters
Information retrieval
Interactive Text Summarization
Knowledge engineering
Large Language Models
Natural language processing
Text summarization
User interfaces
Online AccessGet full text

Cover

More Information
Summary:The overwhelming volume of scientific documents necessitates automatic summarization to assist researchers in efficiently finding relevant data, making informed decisions, and retrieving appropriate answers to their queries. Query-based automatic summarization is to provide a textual summary related to user's initial query. Most of the previous approaches in query-based summarization, only consider the user's initial query to model user's information need, and rarely rely on additional interaction between user and system. This study proposes an interactive multi-document summarization system designed to assist researchers in processing scientific documents. The interactive approach is necessary to refine document selection and improve summary relevance through user feedback. The system utilizes advanced natural language processing techniques to retrieve and summarize relevant content, including query-based summarization to tailor summaries to specific user queries. By incorporating user-generated questions, the system enhances the coherence and pertinence of summaries. The system is tested and evaluated for Persian language. Despite the lack of labeled datasets in the Persian, the proposed approach demonstrates effective summarization through unsupervised methods. User evaluations confirm the system's potential to significantly improve information retrieval and comprehension in scientific research.
ISSN:2643-279X
DOI:10.1109/ICCKE65377.2024.10874524