Other assigned terms:

• alphabet
• ambiguity
• backoff
• backoff n-gram model
• bigram
• bigram model
• character error rate
• characters
• chinese characters
• chinese text
• coefficient
• comparative study
• conditional probabilities
• conditional probability
• corpora
• correlation
• correlation coefficient
• data sparseness
• distribution
• document
• entropy
• error rate
• estimation
• evaluation measure
• evaluation measures
• experimental results
• fact
• finite set
• hypothesis
• kullback-leibler divergence
• language model
• language model probability
• language models
• lexicon
• likelihood
• linear regression model
• linguistics
• measure
• measures
• method
• model perplexity
• model probability
• model size
• n-gram
• n-gram model
• n-gram models
• normalization factor
• ordered list
• perplexity
• phonetic alphabet
• pinyin
• probabilities
• probability
• probability distribution
• probability estimate
• pruning bigram
• pruning threshold
• rank-order correlation coefficient
• regression model
• search space
• style
• target word
• terms
• test corpora
• test data
• test set
• text
• training
• training data
• transcript
• trigram
• unigram
• vocabulary
• vocabulary size
• word
• word error rate
• word pair
• word string
• word strings
• words