ACL RD-TEC 1.0 Summarization of W05-0831
Paper Title:
NOVEL REORDERING APPROACHES IN PHRASE-BASED STATISTICAL MACHINE TRANSLATION
NOVEL REORDERING APPROACHES IN PHRASE-BASED STATISTICAL MACHINE TRANSLATION
Authors: Stephan Kanthak and David Vilar and Evgeny Matusov and Richard Zens and Hermann Ney
Primarily assigned technology terms:
- algorithm
- alignment monotonization
- alignment template system
- automated transducer inference
- automatic evaluation
- automaton
- beam pruning
- bilingual bracketing
- bracketing
- computational linguistics
- computing
- decoding
- dp search
- dynamic programming
- dynamic programming algorithm
- earley parsing
- edit distance algorithm
- em training
- final state
- finite-state automaton
- finite-state transducer
- finite-state transducers
- finite-state translation
- giati monotonization
- giati technique
- giza
- language translation
- levenshtein
- list rescoring
- local alignment
- local reordering
- machine translation
- machine translation system
- model training
- monotonic translation
- monotonization
- parsing
- phrase-based statistical machine translation
- phrase-based translation
- phrase-based translation approach
- programming algorithm
- pruning
- re-estimation
- recognition
- rescoring
- search
- search process
- searching
- segmentation
- sentence reordering
- speech recognition
- speech-to-speech translation
- spoken language translation
- statistical approaches
- statistical machine translation
- statistical machine translation system
- terminology
- transducer
- transducer approach
- transducer inference
- transducers
- transduction
- translation model training
- translation search
- translation system
- translation systems
- weighted finite-state transducer
- weighted finite-state transducers
- weighting
Other assigned terms:
- alignment template
- analogy
- approach
- association for computational linguistics
- automata
- beam
- bilingual training corpus
- bleu
- case
- computational complexity
- conditional probabilities
- corpora
- distribution
- edit distance
- error rate
- experimental results
- grammars
- hypotheses
- ibm model
- ie task
- implementation
- inversion transduction grammars
- iwslt evaluation
- japanese word
- joint probability
- language model
- language pair
- language pairs
- lexicon
- linguistics
- local constraints
- mapping
- measure
- measures
- memory consumption
- method
- multilingual speech
- n-gram
- n-gram models
- nist
- parallel texts
- permutation
- phrase
- phrase level
- probabilities
- probability
- probability distribution
- probability estimates
- procedure
- process
- punctuation
- punctuation marks
- reference translation
- reference translations
- reordering
- search problem
- segments
- sentence
- sentence pair
- sentences
- server
- source sentence
- speech corpus
- spoken language
- statistics
- string edit distance
- symbols
- target language
- target sentence
- target word
- technique
- test corpora
- test corpus
- theory
- toolkit
- training
- training corpus
- training data
- translation model
- translation problem
- translation quality
- translations
- travel expression corpus
- uniform distribution
- uniform probability
- weighting scheme
- window size
- word
- word alignments
- word error rate
- word level
- word order
- words
