ICRM: An Intelligent Citation Recommendation Mechanism Based on BERT and Weighted BoW Models

doi:10.3233/JIFS-237975

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Journal Article > Item 987654321/126326

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/126326

Title:	ICRM: An Intelligent Citation Recommendation Mechanism Based on BERT and Weighted BoW Models
Authors:	Chang, Chih-Yunga;Yang, Yu-Tinga;Zhang, Qiaoyuna;Lin, Yi-Tib;Roy, Diptendu Sinhac
Keywords:	Citation recommendation;TF-IDF;weighted bag of word;BERT
Date:	2024-04-18
Issue Date:	2024-10-02 12:05:40 (UTC+8)
Abstract:	With the field of technology has witnessed rapid advancements, attracting an ever-growing community of researchers dedicated to developing theories and techniques. This paper proposes an innovative ICRM (Intelligent Citation Recommendation Mechanism), designed to automate the process of suggesting the appropriate number of citations for individual brackets within a document. The proposed ICRM comprises three phases: Coarse-grained Weighted Bag of Word (WCBW), Fine-grained SciBERT (FSB) and Citation Adjustment phases. Firstly, the WCBW phase employs TF-IDF to extract keywords from both target and candidate documents, forming vectors that capture word significance along with metadata like authorship, keywords, and titles. It aims to identify relevant papers from a database, serving as initial candidates for each bracket. Secondly, the FSB phase employs the SciBERT model to assess the similarity between candidate documents and the local context around brackets, enhancing the precision of recommendations. It refines this selection by analyzing candidate-document relationships within the proximity of the brackets. Lastly, the Citation Adjustment phase tackles overlapping citations and ensures that recommended citation numbers align with user-defined criteria, resolving issues of imbalance. The simulation results demonstrate that the proposed ICRM outperforms existing models significantly in terms of precision, recall and F1-score.
Relation:	Journal of Intelligent & Fuzzy Systems , vol. 46, pp. 10135-10150
DOI:	10.3233/JIFS-237975
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	47	View/Open

Loading...