Automatic Extraction of Word Sequence Correspondences in Parallel Corpora.
Mihoko KitamuraYuji MatsumotoPublished in: VLC@COLING (1996)
Keyphrases
- automatic extraction
- parallel corpora
- word pairs
- english chinese
- natural language text
- machine translation system
- statistical machine translation
- bilingual dictionaries
- sentence level
- machine translation
- cross language information retrieval
- sentence pairs
- cross lingual
- language independent
- comparable corpora
- relation extraction
- semantic relations
- pairwise
- biomedical literature
- cross language
- co occurrence
- topic models
- parallel corpus
- translation model
- wikipedia articles
- word level
- n gram
- keywords
- multi document summarization
- image retrieval