ACL RD-TEC 1.0 Summarization of P02-1024

Other assigned terms:

• ambiguity
• approach
• array
• asian language
• asian language text
• backoff
• bigram
• case
• character error rate
• characters
• chinese language
• chinese text
• cluster
• cluster number
• clusters
• comparative study
• conditional probability
• convergence
• corpora
• data sets
• data sparseness
• data sparseness problem
• entropy
• error rate
• estimation
• experimental results
• ibm model
• ibm models
• independence assumption
• japanese text
• kanji
• language model
• language model probability
• language models
• leaf
• lexicon
• linguistics
• meaning
• method
• methodology
• model parameter
• model parameters
• model performance
• model probability
• model size
• mutual information
• n-gram
• n-gram model
• n-gram models
• n-grams
• newspaper corpus
• orthography
• parameter settings
• perplexity
• probabilities
• probability
• pruning threshold
• research topic
• root node
• search space
• sparseness problem
• stochastic model
• symbol
• technique
• terms
• test set
• testing data
• text
• text corpora
• theory
• training
• training corpora
• training data
• training instance
• transcript
• tree
• tree structure
• tree structures
• trees
• trigram
• trigram model
• unigram
• word
• word n-gram model
• word sequence
• word string
• word strings
• word trigram
• word trigram model
• words