Detection of OOV words using generalized word models and a semantic class language model.
Thomas SchaafPublished in: INTERSPEECH (2001)
Keyphrases
- language model
- out of vocabulary
- n gram
- translation model
- statistical language modeling
- probabilistic model
- language modeling
- cross lingual
- cross language information retrieval
- word segmentation
- spoken document retrieval
- information retrieval
- document retrieval
- smoothing methods
- speech recognition
- multiword
- test collection
- statistical models
- dependency structure
- query expansion
- relevance model
- word error rate
- document level
- broadcast news
- bag of words
- mixture model
- retrieval model
- word recognition
- text classification
- co occurrence
- naive bayes classification
- statistical machine translation
- ad hoc information retrieval
- named entity recognition
- query translation
- context sensitive
- query terms
- machine translation
- named entities
- word clouds
- document representation
- dirichlet prior
- machine translation system
- word pairs
- semantic similarity
- natural language