Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion

Xiaobao Wu, Xinshuai Dong, Liangming Pan, Thong Nguyen, Anh Tuan Luu


Abstract
Dynamic topic models track the evolution of topics in sequential documents, which have derived various applications like trend analysis. However, existing models suffer from repetitive topic and unassociated topic issues, failing to reveal the evolution and hindering further applications. To address these issues, we break the tradition of simply chaining topics in existing work and propose a novel neural Chain-Free Dynamic Topic Model. We introduce a new evolution-tracking contrastive learning method that builds the similarity relations among dynamic topics. This not only tracks topic evolution but also maintains topic diversity, mitigating the repetitive topic issue. To avoid unassociated topics, we further present an unassociated word exclusion method that consistently excludes unassociated words from discovered topics. Extensive experiments demonstrate our model significantly outperforms state-of-the-art baselines, tracking topic evolution with high-quality topics, showing better performance on downstream tasks, and remaining robust to the hyperparameter for evolution intensities.
Anthology ID:
2024.findings-acl.183
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3088–3105
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.183/
DOI:
10.18653/v1/2024.findings-acl.183
Bibkey:
Cite (ACL):
Xiaobao Wu, Xinshuai Dong, Liangming Pan, Thong Nguyen, and Anh Tuan Luu. 2024. Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3088–3105, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion (Wu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.183.pdf