InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling.
Xiaobao WuXinshuai DongThong NguyenChaoqun LiuLiangming PanAnh Tuan LuuPublished in: AAAI (2023)
Keyphrases
- cross lingual
- monolingual and cross lingual
- topic modeling
- text classification
- probabilistic topic models
- topic models
- machine translation
- language independent
- language modeling
- latent dirichlet allocation
- information retrieval
- word sense
- text mining
- collaborative filtering
- news articles
- transfer learning
- document clustering
- text categorization
- probabilistic model
- high dimensional
- text documents
- bag of words
- language model
- co occurrence
- pairwise