Automatically finding semantically consistent n-grams to add new words in LVCSR systems.
Gwénolé LecorvéGuillaume GravierPascale SébillotPublished in: ICASSP (2011)
Keyphrases
- n gram
- language model
- variable length
- bag of words
- language modeling
- word segmentation
- finite state transducers
- language independent
- part of speech
- viterbi algorithm
- text classification
- statistical language modeling
- information retrieval
- character n grams
- language specific
- web documents
- co occurrence
- natural language