Coarse-grained Cross-lingual Alignment of Comparable Texts with Topic Models and Encyclopedic Knowledge.
Vivi NastaseAngela FahrniPublished in: CoRR (2014)
Keyphrases
- coarse grained
- cross lingual
- monolingual and cross lingual
- word sense
- word alignment
- topic models
- probabilistic topic models
- fine grained
- text documents
- machine translation
- language modeling
- latent dirichlet allocation
- language independent
- topic modeling
- document clustering
- text classification
- co occurrence
- news articles
- text mining
- probabilistic model
- high level
- generative model
- natural language
- protein sequences
- information retrieval
- transfer learning
- natural language processing
- latent topics
- wordnet
- vector space
- knowledge representation