Unsupervised data selection and word-morph mixed language model for tamil low-resource keyword search.
Chongjia NiCheung-Chi LeungLei WangNancy F. ChenBin MaPublished in: ICASSP (2015)
Keyphrases
- language model
- data sets
- keyword search
- speech recognition
- database
- document retrieval
- structured data
- n gram
- machine learning
- co occurrence
- word recognition
- deep web
- cross language information retrieval
- information retrieval systems
- probabilistic model
- data sources
- xml documents
- relational databases
- keywords
- search engine