Utilizing corpus statistics for hindi word sense disambiguation.
Satyendr SinghTanveer J. SiddiquiPublished in: Int. Arab J. Inf. Technol. (2015)
Keyphrases
- word sense disambiguation
- word sense
- machine translation
- wide coverage
- wordnet
- statistical machine translation
- natural language processing
- semantic roles
- information extraction
- named entity recognition
- cross lingual
- linguistic knowledge
- semantic role labeling
- feature generation
- co occurrence
- lexical knowledge
- semantic relatedness
- ambiguous words
- part of speech
- cross language information retrieval
- highly ambiguous
- parallel corpora
- machine learning
- sense disambiguation
- artificial intelligence
- machine translation system
- unsupervised word sense disambiguation
- language identification
- target language
- parallel corpus
- semantic relations
- structured data
- question answering
- feature set
- information retrieval