ACL RD-TEC 1.0 Summarization of W03-1710
Paper Title:
MODELING OF LONG DISTANCE CONTEXT DEPENDENCY IN CHINESE
MODELING OF LONG DISTANCE CONTEXT DEPENDENCY IN CHINESE
Primarily assigned technology terms:
- back-off modeling
- character conversion
- chinese word segmentation
- computational linguistics
- computing
- language modeling
- language processing
- likelihood estimation
- linear interpolation
- machine translation
- mandarin speech recognition
- maximum likelihood
- maximum likelihood estimation
- mi-ngram modeling
- mi-trigram modeling
- modeling
- natural language processing
- ngram modeling
- processing
- recognition
- segmentation
- smoothing
- smoothing techniques
- speech recognition
- statistical language modeling
- word segmentation
- word segmentation task
Other assigned terms:
- annotation
- approach
- bigram
- bigram model
- case
- characters
- chinese characters
- chinese word
- concept
- context dependency
- data sparseness
- data sparseness problem
- distribution
- entropy
- error rate
- estimation
- f-measure
- hypothesis
- information content
- interpolation
- lexicon
- likelihood
- linguistics
- measure
- measures
- model size
- modeling power
- mutual information
- natural language
- news corpus
- ngram
- ngram model
- perplexity
- pinyin
- precision
- probabilities
- probability
- probability distribution
- relation
- sparseness problem
- training
- training data
- trigram
- trigram model
- window size
- word
- word pair
- word string
- word strings
- words
