Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring.
Zihan LiuYan XuGenta Indra WinataPascale FungPublished in: WMT (2) (2019)
Keyphrases
- language model
- machine translation
- n gram
- out of vocabulary
- statistical machine translation
- language independent
- translation model
- chinese english
- language modeling
- word level
- cross language information retrieval
- cross lingual
- spoken document retrieval
- speech recognition
- natural language processing
- document retrieval
- machine translation system
- information retrieval
- word alignment
- probabilistic model
- test collection
- query expansion
- target language
- retrieval model
- word sense disambiguation
- information extraction
- parallel corpora
- ad hoc information retrieval
- word segmentation
- context sensitive
- parallel corpus
- part of speech
- vector space model
- document level
- query terms
- natural language
- semi supervised
- query translation
- retrieval effectiveness
- text classification
- statistical models
- question answering
- text mining
- multiword
- cross language retrieval
- novelty detection