Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring.
Zihan LiuYan XuGenta Indra WinataPascale FungPublished in: CoRR (2019)
Keyphrases
- language model
- machine translation
- n gram
- statistical machine translation
- out of vocabulary
- language independent
- chinese english
- language modeling
- word level
- cross lingual
- translation model
- speech recognition
- word alignment
- query expansion
- probabilistic model
- word sense disambiguation
- information retrieval
- machine translation system
- document retrieval
- natural language processing
- spoken document retrieval
- word segmentation
- retrieval model
- parallel corpora
- context sensitive
- test collection
- parallel corpus
- cross language information retrieval
- natural language
- target language
- information extraction
- query terms
- vector space model
- part of speech
- pseudo relevance feedback
- document collections
- semi supervised
- ad hoc information retrieval