Subword Segmentation for Machine Translation Based on Grouping Words by Potential Roots.
Janis ZutersGus StrazdsPublished in: Balt. J. Mod. Comput. (2019)
Keyphrases
- machine translation
- word sense disambiguation
- word segmentation
- n gram
- out of vocabulary
- language independent
- word alignment
- word level
- cross lingual
- cross language information retrieval
- language specific
- pos tagging
- multilingual documents
- target language
- natural language processing
- natural language generation
- chinese english
- parallel corpus
- spoken document retrieval
- information extraction
- language processing
- english chinese
- natural language
- statistical machine translation
- parallel corpora
- language resources
- query translation
- language modeling
- machine translation system
- part of speech
- word order
- bilingual dictionaries
- source language
- brazilian portuguese