Incorporating monolingual corpora into bilingual latent semantic analysis for crosslingual LM adaptation.
Yik-Cheung TamTanja SchultzPublished in: ICASSP (2009)
Keyphrases
- latent semantic analysis
- parallel corpus
- chinese english
- co occurrence
- cross lingual
- language modeling
- semantic space
- parallel texts
- information retrieval
- wordnet
- machine translation
- language model
- latent semantic indexing
- singular value decomposition
- cross language information retrieval
- word alignment
- document clustering
- statistical machine translation
- parallel corpora
- tf idf
- comparable corpora
- text summarization
- query translation
- text documents
- cross language
- latent dirichlet allocation
- language independent
- query expansion
- topic modeling
- machine translation system
- text corpora
- vector space model
- document retrieval
- visual words