A language-independent and fully unsupervised approach to lexicon induction and part-of-speech tagging for closely related languages.
Yves ScherrerBenoît SagotPublished in: LREC (2014)
Keyphrases
- language independent
- closely related
- fully unsupervised
- multi lingual
- n gram
- cross lingual
- machine translation
- word forms
- natural language processing
- text classification
- text retrieval
- cross language
- np hard
- natural language
- part of speech
- parallel corpora
- word segmentation
- word level
- language specific
- bayesian networks
- machine learning
- digital libraries
- keywords
- reinforcement learning