Extended word similarity based clustering on unsupervised PoS induction to improve English-Indonesian statistical machine translation.
Herry SujainiAyu PurwariantiArry Akhmad Arman KuspriyantoPublished in: O-COCOSDA/CASLRE (2013)
Keyphrases
- statistical machine translation
- machine translation
- grammar induction
- training corpus
- word alignment
- machine translation system
- word sense disambiguation
- cross language information retrieval
- unsupervised learning
- phrase based smt
- cross lingual
- parallel corpus
- pos tagging
- translation model
- language independent
- language model
- clustering method
- natural language processing
- co occurrence
- language processing
- machine learning
- parallel corpora
- chinese english
- minimum error rate
- part of speech
- multiword
- natural language generation
- source language
- k means
- natural language
- word level
- context sensitive
- n gram
- information extraction
- clustering algorithm
- search engine