A Hybrid Approach for Automatic Extraction of Bilingual Multiword Expressions from Parallel Corpora.
Nasredine SemmarPublished in: LREC (2018)
Keyphrases
- automatic extraction
- multiword
- parallel corpora
- statistical machine translation
- bilingual dictionaries
- biomedical literature
- context sensitive
- machine translation
- cross language information retrieval
- labor intensive
- relation extraction
- machine translation system
- language model
- cross lingual
- natural language
- language independent
- text clustering
- word pairs
- document representation
- wikipedia articles
- cross language
- part of speech
- machine learning
- semantic knowledge
- natural language text
- named entities