Optimizing Tokenization Choice for Machine Translation across Multiple Target Languages.
Nasser ZalmoutNizar HabashPublished in: Prague Bull. Math. Linguistics (2017)
Keyphrases
- machine translation
- multiple targets
- target language
- language independent
- cross lingual
- statistical machine translation
- language specific
- multilingual documents
- multilingual retrieval
- machine translation system
- language resources
- data association
- source language
- query translation
- parallel corpora
- bilingual dictionaries
- information extraction
- word sense disambiguation
- visual tracking
- natural language processing
- cross language information retrieval
- particle filter
- multiple objects
- natural language
- comparable corpora
- particle filtering
- dublin city university
- language processing
- word level
- multilingual information retrieval
- named entities
- linguistic resources
- chinese english
- grammar induction
- multi sensor
- cross language
- n gram
- word order
- machine learning
- dynamic programming
- moving target
- artificial intelligence