ACL RD-TEC 1.0 Summarization of W03-1002
Paper Title:
STATISTICAL MACHINE TRANSLATION USING COERCIVE TWO-LEVEL SYNTACTIC TRANSDUCTION
STATISTICAL MACHINE TRANSLATION USING COERCIVE TWO-LEVEL SYNTACTIC TRANSDUCTION
Authors: Charles Schafer and David Yarowsky
Primarily assigned technology terms:
- chunker
- chunking
- decoder
- decoding
- decomposition
- electronic translation
- finite state
- finite state machine
- finite-state framework
- french-to-english translation
- fsm construction
- fsm toolkit
- giza
- handwriting recognition
- induction
- language modeling
- learning
- lemmatization
- lemmatizer
- machine translation
- majority voting
- modeling
- modelling
- noisy channel model
- parser
- part-of-speech tagging
- phrase chunking
- phrase translation
- pos tagger
- pos tagging
- ranking
- recognition
- rescoring
- search
- searching
- sentence translation
- sequence translation
- shallow syntactic analysis
- simple majority voting
- smt system
- sri language modeling
- statistical machine translation
- syntactic analysis
- tagger
- tagging
- tokenizer
- transducers
- transduction
- transliteration
- voting
- word alignment
- word generation
- word translation
Other assigned terms:
- adjective
- approach
- backoff
- bilingual corpus
- bleu
- bleu score
- case
- chunk
- chunks
- composition
- concept
- context free grammars
- corpora
- correlation
- data consortium
- determiners
- dictionary
- distribution
- english part-of-speech
- english verb
- foreign language
- foreign word
- foreign words
- french
- french word
- frequency distribution
- generation
- grammars
- grounding
- handwriting
- human knowledge
- human translation
- hypotheses
- implementation
- index
- knowledge
- language model
- language modeling toolkit
- language pair
- lattice
- lattices
- lemma
- lexical transfer
- lexical translation
- linguistic
- linguistic data
- linguistic data consortium
- meaning
- method
- modeling toolkit
- noisy channel
- nouns
- parallel bilingual corpus
- parallel corpora
- parallel corpus
- parse
- parse tree
- part of speech
- part-of-speech
- parts of speech
- penn treebank
- penn treebank corpus
- phrase
- phrase translation model
- phrase type
- pos tag
- prepositions
- probabilities
- probability
- probability distribution
- relative frequency
- reordering
- sentence
- sentence structure
- sentence-level model
- sentences
- sentential context
- sparse data
- subtrees
- symbol
- symbols
- syntactic transduction
- tags
- target languages
- term
- test set
- toolkit
- training
- training corpora
- training corpus
- training data
- training set
- transfer model
- translation dictionary
- translation model
- translation probabilities
- translation probability
- translations
- tree
- treebank
- treebank corpus
- trigram
- trigram language model
- understanding
- verb
- word
- word alignment links
- word alignments
- word sequences
- word string
- words
