The robustness of an almost-parsing language model given errorful training data.
Wen WangMary P. HarperAndreas StolckePublished in: ICASSP (1) (2003)
Keyphrases
- language model
- training data
- language modeling
- document retrieval
- n gram
- probabilistic model
- language modelling
- information retrieval
- natural language processing
- speech recognition
- statistical language models
- decision trees
- dependency structure
- query expansion
- mixture model
- learning algorithm
- retrieval model
- smoothing methods
- ad hoc information retrieval
- training set
- translation model
- context sensitive
- test collection
- relevance model
- vector space model
- query terms
- statistical machine translation
- prior knowledge
- labeled data
- supervised learning
- document length
- natural language
- search engine
- word clouds