BPE beyond Word Boundary: How NOT to use Multi Word Expressions in Neural Machine Translation.
Dipesh KumarAvijit ThawaniPublished in: Insights@ACL (2022)
Keyphrases
- multiword
- machine translation
- statistical machine translation
- natural language
- bilingual dictionaries
- context sensitive
- word sense disambiguation
- part of speech
- natural language processing
- language independent
- word alignment
- target language
- language model
- cross lingual
- cross language information retrieval
- machine translation system
- information extraction
- text clustering
- document representation
- word level
- query translation
- parallel corpora
- keywords
- parallel corpus