ACL RD-TEC 1.0 Summarization of P06-1009

Other assigned terms:

• 10-fold cross-validation
• affixes
• aligned corpus
• alignment error rate
• alignment model
• alignment models
• approach
• association for computational linguistics
• beam
• bilingual corpus
• bilingual dictionary
• break
• candidate translation
• case
• characters
• coefficient
• conditional distribution
• conditional model
• conditional probability
• conditional probability distribution
• corpora
• crf model
• data set
• data sets
• density function
• determiners
• dice
• dice coefficient
• dictionaries
• dictionary
• discriminative model
• distribution
• error rate
• estimation
• experimental results
• f-score
• feature
• feature set
• feature types
• french
• gaussian prior
• generalisation
• generative model
• generative models
• gold standard
• heuristic
• heuristics
• ibm models
• implementation
• index
• joint probability
• knowledge
• labeling
• language pair
• language pairs
• lexical features
• lexicon
• likelihood
• linguistics
• log-likelihood
• log-linear model
• log-linear models
• markup
• measure
• method
• model parameters
• noise
• parallel corpus
• part-of-speech
• part-of-speech tags
• parts-of-speech
• partsof-speech
• phrase
• phrase level
• pos tag
• posterior
• posterior probability
• precision
• prefixes and suffixes
• prior distribution
• probabilities
• probability
• probability density
• probability density function
• probability distribution
• process
• sentence
• sentence position
• sentences
• sequence model
• source language
• source sentence
• sparse data
• statistics
• suffixes
• tags
• target sentence
• target word
• terms
• test data
• test set
• testing set
• trained model
• training
• training corpus
• training data
• training set
• translation direction
• translation pair
• translation pairs
• translation probabilities
• translation probability
• translation quality
• translation score
• translation table
• translation task
• word
• word alignments
• word association
• word pair
• words