Word and Sentence Tokenization with Hidden Markov Models.
Bryan JurishKay-Michael WürznerPublished in: J. Lang. Technol. Comput. Linguistics (2013)
Keyphrases
- hidden markov models
- sentence level
- n gram
- noun phrases
- handwritten words
- word level
- keyword spotting
- character n grams
- named entities
- viterbi algorithm
- part of speech
- co occurrence
- conditional random fields
- speech recognition
- markov model
- natural language
- markov models
- sequential data
- gesture recognition
- sequence classification
- hidden state
- word segmentation
- automatic speech recognition
- hidden states
- continuous hidden markov models
- variable length
- cross language
- document images
- keywords
- handwritten text recognition
- information retrieval