Document Type

Conference Paper

Publication Date

2025

DOI

10.18653/v1/2025.emnlp-main.670

Publication Title

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing

Pages

13259-13275

Conference Name

2025 Conference on Empirical Methods in Natural Language Processing, November 4-9, 2025, Suzhou, China

Abstract

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.

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.

Original Publication Citation

Liu, J., Yan, J., Zhu, C., Liu, X., Li, Q., & Rao, Y. (2025). Neural topic modeling via contextual and graph information fusion. In C. Christodoulopoulos, T. Chakraborty, C. Rose & V. Peng (Eds.), Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 13259-13275). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.emnlp-main.670

Download

Share

COinS