Conference

Neural Topic Modeling via Contextual and Graph Information Fusion

Bibliographic Details
Title: Neural Topic Modeling via Contextual and Graph Information Fusion
Authors: Liu, Jiyuan, Yan, Jiaxing, Zhu, Chunjiang, Liu, Xingyu, Li, Qing, Rao, Yanghui
Source: Computer Science Faculty Publications
Publisher Information: ODU Digital Commons
Publication Year: 2025
Collection: Old Dominion University: ODU Digital Commons
Subject Terms: Graph theory—Data processing, Information storage and retrieval systems—Automatic indexing, Knowledge representation (Information theory), Machine learning—Statistical methods, Natural language processing (Computer science), Semantic networks (Information theory), Text mining, Topic modeling (Information retrieval), Artificial Intelligence and Robotics, Computer Sciences, Data Science
Description: Topic modeling is a powerful unsupervised tool for knowledge discovery. However, existing work struggles with generating limited-quality topics that are uninformative and incoherent, which hindering interpretable insights from managing textual data. In this paper, we improve the original variational autoencoder framework by incorporating contextual and graph information to address the above issues. First, the encoder utilizes topic fusion techniques to combine contextual and bag-of-words information well, and meanwhile exploits the constraints of topic alignment and topic sharpening to generate informative topics. Second, we develop a simple word co-occurrence graph information fusion strategy that efficiently increases topic coherence. On three benchmark datasets, our new framework generates more coherent and diverse topics compared to various baselines, and achieves strong performance on both automatic and manual evaluations.
Document Type: conference object
File Description: application/pdf
Language: unknown
Relation: https://digitalcommons.odu.edu/computerscience_fac_pubs/413; https://digitalcommons.odu.edu/context/computerscience_fac_pubs/article/1418/viewcontent/Zhu_2025_NeuralTopicModelingviaContextualandGraphInformationOCR.pdf
DOI: 10.18653/v1/2025.emnlp-main.670
Availability: https://digitalcommons.odu.edu/computerscience_fac_pubs/413
https://doi.org/10.18653/v1/2025.emnlp-main.670
https://digitalcommons.odu.edu/context/computerscience_fac_pubs/article/1418/viewcontent/Zhu_2025_NeuralTopicModelingviaContextualandGraphInformationOCR.pdf
Rights: © 2025 Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International (CC BY 4.0) License .
Accession Number: edsbas.F57780E9
Database: BASE
Description
DOI:10.18653/v1/2025.emnlp-main.670