Building Comparable Corpora Based on Bilingual LDA Model.
Zede ZhuMiao LiLei ChenZhenxin YangPublished in: ACL (2) (2013)
Keyphrases
- comparable corpora
- parallel corpora
- cross language information retrieval
- bilingual lexicon
- news articles
- lda model
- language modeling
- machine translation
- topic models
- latent dirichlet allocation
- text corpora
- text documents
- cross lingual
- word pairs
- query translation
- bi directional
- word alignment
- bilingual dictionaries
- cross language
- linguistic resources
- generative model
- machine translation system
- statistical machine translation
- translation model
- information retrieval
- topic modeling
- language independent
- document collections