ACL RD-TEC 1.0 Summarization of W03-1703
Paper Title:
UTTERANCE SEGMENTATION USING COMBINED APPROACH BASED ON BI-DIRECTIONAL N-GRAM AND MAXIMUM ENTROPY
UTTERANCE SEGMENTATION USING COMBINED APPROACH BASED ON BI-DIRECTIONAL N-GRAM AND MAXIMUM ENTROPY
Authors: Ding Liu and Chengqing Zong
Primarily assigned technology terms:
- algorithm
- automatic recognizer
- automatic speech recognition
- beam search
- boundary detection
- computing
- decision trees
- disambiguation
- discourse processing
- generalized iterative scaling
- interfaces
- iterative scaling
- kneser-ney smoothing
- language translation
- linguistic modeling
- matching
- maximum entropy
- maximum entropy approach
- maximum entropy method
- maximum entropy model
- model training
- modeling
- n-gram segmentation
- n-gram-based segmentation
- n-gram-based segmentation method
- nn algorithm
- processing
- reading
- recognition
- recognizer
- reverse n-gram segmentation
- search
- segmentation
- segmentation method
- sentence boundary detection
- sequence segmentation
- smoothing
- speech recognition
- spoken language translation
- syntactic analysis
- taggers
- template matching
- trigram speech recognition
- user interface
- user interfaces
- utterance segmentation
- weighting
- word detection
Other assigned terms:
- ambiguity
- approach
- beam
- brown corpus
- case
- characters
- chinese characters
- conditional probability
- corpora
- dialogues
- dictionary
- discourse
- distribution
- entropy
- experimental results
- feature
- intention
- joint probability
- joint probability distribution
- language model
- language models
- lexical context
- lexical information
- likelihood
- linguistic
- linguistic model
- markov chain
- maximum-entropy-based model
- method
- n-gram
- n-gram language model
- n-gram model
- n-gram models
- n-grams
- natural language
- natural language user
- part of speech
- part-of-speech
- part-of-speech information
- pauses
- precision
- probabilities
- probability
- probability distribution
- punctuation
- punctuation marks
- recognition model
- segmentation accuracy
- segments
- semantic
- sentence
- sentence boundaries
- sentence boundary
- sentences
- speech information
- spoken language
- suffix
- suffixes
- symbols
- tags
- test corpora
- test corpus
- test set
- text
- training
- training corpora
- training corpus
- training data
- transcripts
- trees
- trigram
- understanding
- user
- user utterances
- utterance
- word
- word sequence
- word sequences
- words
