Using Multilingual Topic Models for Improved Alignment in English-Hindi MT.
Diptesh KanojiaAditya JoshiPushpak BhattacharyyaMark James CarmanPublished in: ICON (2015)
Keyphrases
- machine translation
- cross lingual
- monolingual and cross lingual
- topic models
- word alignment
- language independent
- cross language information retrieval
- comparable corpora
- indian languages
- cross language
- parallel corpus
- topic modeling
- machine translation system
- statistical machine translation
- latent dirichlet allocation
- natural language processing
- target language
- query translation
- text corpora
- natural language
- text mining
- information extraction
- probabilistic model
- translation model
- text documents
- language identification
- parallel corpora
- word sense disambiguation
- latent topics
- language modeling
- gibbs sampling
- probabilistic latent semantic analysis
- information retrieval
- latent topic models
- source language
- latent variables
- machine learning