Semi-supervised transliteration mining from parallel and comparable corpora.
Walid AransaHolger SchwenkLoïc BarraultPublished in: IWSLT (2012)
Keyphrases
- cross language information retrieval
- comparable corpora
- semi supervised
- web corpora
- machine translation
- bilingual dictionaries
- data mining
- bilingual lexicon
- cross language
- text mining
- parallel corpora
- semi supervised learning
- unlabeled data
- word pairs
- text corpora
- query translation
- linguistic resources
- language modeling
- named entities
- labeled data
- active learning
- cross lingual
- text retrieval
- translation model
- co occurrence
- natural language processing
- knowledge discovery
- pairwise