Mining Complex Predicates In Hindi Using A Parallel Hindi-English Corpus.
R. Mahesh K. SinhaPublished in: MWE@IJCNLP (2009)
Keyphrases
- statistical machine translation
- language identification
- machine translation
- indian languages
- contextual features
- comparable corpora
- proper names
- named entity recognition
- cross lingual
- target language
- link grammar
- english text
- spoken language
- machine translation system
- information retrieval
- knowledge discovery
- mono lingual
- noun phrases
- data mining
- natural language
- source language
- shared memory
- open domain
- text mining
- language model
- machine learning
- person names
- information extraction
- broad coverage
- parallel corpora
- language modeling
- speaker identification
- frequent patterns
- sequential patterns
- pattern mining
- word pairs
- optical character recognition
- cross language information retrieval
- parallel processing