ACL RD-TEC 1.0 Summarization of P01-1027
Paper Title:
REFINED LEXICON MODELS FOR STATISTICAL MACHINE TRANSLATION USING A MAXIMUM ENTROPY APPROACH
REFINED LEXICON MODELS FOR STATISTICAL MACHINE TRANSLATION USING A MAXIMUM ENTROPY APPROACH
Authors: Ismael García-Varea and Franz J. Och and Hermann Ney and Francisco Casacuberta
Primarily assigned technology terms:
- algorithm
- approximation
- computing
- corresponding training
- direct translation
- disambiguation
- extraction algorithm
- feature selection
- giza
- hidden markov
- hidden markov models
- iterative scaling
- language modeling
- language processing
- machine translation
- machine translation system
- machine translation systems
- maximum approximation
- maximum entropy
- maximum entropy approach
- maximum entropy model
- me training
- modeling
- natural language processing
- normalization
- processing
- recognition
- rescoring
- search
- sense disambiguation
- sentence splitting
- speech recognition
- speech translation
- splitting
- statistical machine translation
- statistical machine translation system
- statistical training
- statistical translation
- training procedure
- translation process
- translation system
- translation systems
- viterbi
- viterbi alignment
- word reordering
- word sense disambiguation
- word-to-word alignment
Other assigned terms:
- alignment models
- appointment scheduling
- approach
- bilingual corpus
- case
- concept
- context information
- contextual information
- data sparseness
- data sparseness problem
- decision rule
- dialog
- dialog act
- edit distance
- english vocabulary
- entropy
- entropy models
- error rate
- events
- experimental results
- fact
- feature
- hypotheses
- hypothesis
- language model
- lexicon
- lexicon model
- likelihood
- linguistic
- mapping
- markov models
- maximum entropy models
- meaning
- measure
- mood
- natural language
- normalization factor
- parallel corpus
- part-of-speech
- part-of-speech information
- perplexity
- perplexity measure
- perplexity reduction
- possible translation
- probability
- procedure
- process
- reference translation
- reordering
- search space
- semantic
- semantic features
- semantic information
- semantic meaning
- sentence
- sentence boundaries
- sentence pair
- sentences
- source language
- sparseness problem
- speech translation task
- statistical framework
- stochastic model
- string translation model
- syntactic constituent
- syntactic information
- syntactic structures
- target language
- target language model
- target language string
- target sentence
- target string
- target word
- terms
- test corpus
- toolkit
- training
- training corpus
- training data
- translation model
- translation models
- translation probability
- translation quality
- translation task
- translations
- vocabulary
- word
- word classes
- word error rate
- word order
- word pair
- word sense
- wordnet
- words
