P08-1011 in which positions for measure word generation are identified . Based on contextual
P08-1011 may cause low quality of measure word generation . In addition , sometimes the
P08-1011 improve the quality of measure word generation . We also compared the performance
P05-1039 consistently does better than the simpler word generation probability model . Looking at
I05-3034 Word Generation The procedure of word generation involves two steps : ( 1 ) generation
A92-1034 can be compiled into either a word generation program or a word parsing program
P08-1011 precision and recall in measure word generation . 1 Introduction In linguistics
E09-1013 senses as a latent variable in the word generation process . In this case the model
A00-1027 shorter length of analyses and the word generation possibilities are computed and
P08-1011 overcome the disadvantage of measure word generation in a general SMT system , this
N13-1117 both these models the spurious word generation is controlled by a binomial distribution
I05-3034 They are described below . 2.1 Word Generation The procedure of word generation
P08-1011 model the probability of measure word generation by utilizing rich lexical and
P08-1011 model the probability of measure word generation by utilizing lexical and syntactic
E87-1006 describing the logic rules for the word generation . Other two morphologic systems
J12-3007 manner . At any given stage of the word generation by the SLM , the exposed headwords
P08-1011 suggestions . <title> Measure Word Generation for English-Chinese SMT Systems
P08-1011 not deal well with the measure word generation in general due to data sparseness
E85-1033 descriptions . 4.6 Word Generation Word generation uses the same organization of
E85-1033 list of word descriptions . 4.6 Word Generation Word generation uses the same
hide detail