ACL RD-TEC 1.0 Summarization of W06-1608
Paper Title:
THE IMPACT OF PARSE QUALITY ON SYNTACTICALLY-INFORMED STATISTICAL MACHINE TRANSLATION
THE IMPACT OF PARSE QUALITY ON SYNTACTICALLY-INFORMED STATISTICAL MACHINE TRANSLATION
Authors: Chris Quirk and Simon Corston-Oliver
Primarily assigned technology terms:
- beam search
- blind evaluation
- bootstrap
- classifier
- computational linguistics
- computer documentation
- data annotation
- database
- decoder
- decoding
- dependency analysis
- dependency parser
- dependency parsing
- english-to-japanese treelet smt
- giza
- identification
- kneser-ney smoothing
- language processing
- lexical weighting
- machine translation
- machine translation system
- machine translation systems
- morphology
- natural language processing
- parser
- parser evaluation
- parsers
- parsing
- pos tagger
- processing
- reading
- right-branching
- root identification
- scoring
- search
- smoothing
- smt system
- statistical machine translation
- statistical machine translation system
- syntactic analysis
- syntactically-informed statistical machine translation
- tagger
- topicalization
- translation process
- translation system
- translation systems
- treebank training
- treelet translation
- weighting
- word alignment
Other assigned terms:
- aligned sentence
- annotation
- approach
- association for computational linguistics
- beam
- bleu
- bleu score
- case
- cohesion
- community
- compounding
- constituent order
- corpora
- correlations
- dependency graph
- dependency link
- dependency relation
- dependency representation
- dependency structure
- dependency tree
- dependency trees
- distribution
- english penn treebank
- english text
- feature
- feature vector
- formal theory
- genre
- heuristics
- inflectional morphology
- inter-annotator agreement
- japanese translation
- language model
- language pair
- language pairs
- lexeme
- lexical features
- lexical information
- lexical item
- lexical items
- lexicon
- linguistic
- linguistics
- log-linear combination
- machine translation output
- machine translation quality
- mappings
- measure
- method
- mood
- natural language
- noise
- noun compounding
- noun phrase
- noun phrases
- parallel corpus
- parse
- parsing approach
- part-of-speech
- penn treebank
- phrase
- preposition
- prepositional phrase
- prepositional phrases
- prepositions
- probability
- probability distribution
- process
- punctuation
- queries
- relation
- relative clauses
- relative frequency
- root node
- semantic
- semantic domain
- sentence
- sentences
- source sentence
- stem
- subgraph
- subordinate clause
- syntactic relations
- syntax
- tags
- target language
- target language model
- target languages
- target sentence
- technical text
- term
- terms
- test data
- text
- theory
- tokens
- topics
- training
- training data
- training material
- training set
- training text
- training time
- translation output
- translation pair
- translation pairs
- translation quality
- translations
- tree
- treebank
- trees
- trigram
- uniform probability
- verb
- verb forms
- vocabulary
- wall street journal corpus
- wall street journal text
- weight vector
- word
- word count
- word order
- words
