ACL RD-TEC 1.0 Summarization of W06-3117
Paper Title:
STOCHASTIC INVERSION TRANSDUCTION GRAMMARS FOR OBTAINING WORD PHRASES FOR PHRASE-BASED STATISTICAL MACHINE TRANSLATION
STOCHASTIC INVERSION TRANSDUCTION GRAMMARS FOR OBTAINING WORD PHRASES FOR PHRASE-BASED STATISTICAL MACHINE TRANSLATION
Authors: Joan Andreu Sánchez and José Miguel Benedí
Primarily assigned technology terms:
- algorithm
- bilingual parsing
- bracketing
- decoder
- dynamic programing
- learning
- machine translation
- machine translation approach
- machine translation system
- machine translation systems
- parser
- parsers
- parsing
- parsing algorithm
- phrase translation
- phrase-based machine translation
- phrase-based statistical machine translation
- phrase-based translation
- sentence alignment
- statistical machine translation
- statistical machine translation system
- statistical translation
- transduction
- translation system
- translation systems
- viterbi-like parsing
- viterbi-like parsing algorithm
- word alignment
Other assigned terms:
- aligned corpus
- alignment probability
- approach
- bilingual corpora
- bilingual training corpus
- bleu
- bleu score
- bracketed corpora
- bracketed corpus
- context-free grammars
- corpora
- derivation
- derivations
- empty string
- europarl corpus
- fact
- finite set
- formalism
- grammar
- grammars
- input string
- inversion transduction grammars
- language model
- language pair
- language pairs
- lexical rules
- linguistic
- linguistic information
- measure
- method
- parallel corpora
- parse
- parse tree
- parsed corpus
- phrase
- phrase-based system
- probability
- process
- root node
- segments
- sentence
- sentences
- sentential form
- source language
- source sentence
- stochastic context-free grammars
- structural information
- symbols
- syntactic rule
- syntactic rules
- target language
- target sentence
- test set
- time complexity
- training
- training corpora
- training corpus
- training set
- translation models
- translation quality
- translation table
- translations
- tree
- treebank
- treebank corpus
- upenn treebank
- word
- words
