ACL RD-TEC 1.0 Summarization of P06-2124

Other assigned terms:

• accent
• alignment accuracy
• alignment model
• alignment models
• approach
• association for computational linguistics
• baseline model
• bleu
• bleu score
• bleu scores
• case
• chinese words
• co-occurrence
• co-occurrence count
• coherence
• conditional distribution
• conditional probability
• data sets
• data sparseness
• data sparsity
• development set
• dirichlet allocation
• distribution
• document
• documentpair
• end-user
• english sentence
• estimation
• evaluations
• exponential model
• f-measure
• formalism
• french
• french sentence
• french word
• geometric mean
• heuristic
• heuristics
• ibm models
• index
• interpolation
• kullback-leibler divergence
• language model
• large training
• lexicon
• lexicon entries
• likelihood
• linguistic
• linguistic granularity
• linguistics
• log-likelihood
• maps
• model parameters
• nist
• parallel corpus
• posterior
• precision
• priori
• probabilities
• probability
• probability density
• process
• query
• seed
• segments
• sentence
• sentence level
• sentences
• source language
• source sentence
• style
• target language
• target languages
• target sentence
• test data
• test set
• theory
• tokens
• topical admixture
• topical context
• topics
• training
• training data
• translation lexicon
• translation model
• translation models
• translation quality
• translations
• treebank
• trigram
• trigram language model
• uniform distribution
• vocabulary
• word
• word alignment accuracy
• word alignments
• word distribution
• word level
• words