ACL RD-TEC 1.0 Summarization of C02-1072
Paper Title:
A COMPARATIVE EVALUATION OF DATA-DRIVEN MODELS IN TRANSLATION SELECTION OF MACHINE TRANSLATION
A COMPARATIVE EVALUATION OF DATA-DRIVEN MODELS IN TRANSLATION SELECTION OF MACHINE TRANSLATION
Authors: Yu-Seop Kim and Jeong-Ho Chang and Byoung-Tak Zhang
Primarily assigned technology terms:
- 5-fold cross validation
- algorithm
- classiflcation
- comparative evaluation
- cross validation
- decomposition
- dictionary search
- dictionary search method
- direct matching
- disambiguation
- em algorithm
- factor analysis
- indexing
- information retrieval
- k-nearest neighbor
- k-nn
- knowledge bases
- language modelling
- latent semantic analysis
- learning
- list training
- machine translation
- matching
- measuring
- modelling
- morphology
- morphology analysis
- nearest neighbors
- parameter estimation
- parser
- sampling
- search
- search method
- semantic analysis
- sense disambiguation
- singular value decomposition
- statistical technique
- syntactic parser
- translation process
- translation selection
- validation
- word sense disambiguation
Other assigned terms:
- break
- case
- co-occurrence
- collocation
- computational complexity
- contextual information
- corpora
- data sparseness
- data sparseness problem
- dictionaries
- dictionary
- discourse
- distribution
- distributional soundness
- document
- english verb
- estimation
- euclidean distance
- fact
- grammatical relation
- grammatical relations
- implementation
- knowledge
- large text corpora
- latent class
- latent semantic
- latent semantic space
- likelihood
- likelihood function
- log-likelihood
- meaning
- method
- news corpus
- occurrence frequency
- passage
- phrase
- phrase attachment
- preposition
- preposition phrase
- process
- query
- relation
- selection accuracy
- selectional restriction
- semantic
- semantic similarity
- semantic space
- semantic structure
- semantic structures
- semantic type
- sentences
- similarity between words
- sparseness problem
- stems
- technique
- terms
- test set
- text
- text corpora
- text documents
- text passage
- thesaurus
- training
- training example
- training examples
- translation accuracy
- translations
- trec data
- verb
- vocabulary
- wall street journal corpus
- word
- word distribution
- word sense
- words
