Abstract
Most existing topic models rely on bag-of-words (BOW) representation, which limits their ability to capture word order information and leads to challenges with out-of-vocabulary (OOV) words in new documents. Contextualized word embeddings, however, show superiority in word sense disambiguation and effectively address the OOV issue. In this work, we introduce a novel neural topic model called the Contextlized Word Topic Model (CWTM), which integrates contextualized word embeddings from BERT. The model is capable of learning the topic vector of a document without BOW information. In addition, it can also derive the topic vectors for individual words within a document based on their contextualized word embeddings. Experiments across various datasets show that CWTM generates more coherent and meaningful topics compared to existing topic models, while also accommodating unseen words in newly encountered documents.- Anthology ID:
- 2024.lrec-main.382
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 4273–4286
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.382
- DOI:
- Cite (ACL):
- Zheng Fang, Yulan He, and Rob Procter. 2024. CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4273–4286, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling (Fang et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.382.pdf