ACL RD-TEC 1.0 Summarization of W02-1019
Paper Title:
MINIMUM BAYES-RISK WORD ALIGNMENTS OF BILINGUAL TEXTS
MINIMUM BAYES-RISK WORD ALIGNMENTS OF BILINGUAL TEXTS
Authors: Shankar Kumar and William Byrne
Primarily assigned technology terms:
- algorithm
- alignment loss function
- alignment process
- automatic alignment
- automatic speech recognition
- automatic word alignment
- bitext alignment
- clustering
- computational linguistics
- decoder
- decoding
- dictionary construction
- document retrieval
- finite state
- finite state composition
- finite state machine
- finite state transducer
- finite state translation
- forward-backward algorithm
- fsm toolkit
- giza
- information retrieval
- language processing
- learning
- learning procedure
- likelihood decoding
- likelihood estimation
- linguistic analysis
- loss function
- machine translation
- machine translation systems
- maximum likelihood
- maximum likelihood estimation
- mbr decoding
- model rescoring
- modeling
- mt system
- multilingual document retrieval
- natural language processing
- parser
- parsers
- pos tagger
- processing
- pruning
- recognition
- rescoring
- search
- sentence alignment
- shortest-path
- speech recognition
- statistical learning
- statistical machine translation
- statistical mt
- statistical translation
- tagger
- taggers
- transducer
- translation systems
- translator
- translators
- tuning
- word alignment
- word translation
Other assigned terms:
- alignment error rate
- alignment models
- ambiguity
- annotation
- approach
- association for computational linguistics
- baseline performance
- bilingual corpora
- bitext
- case
- cluster
- clusters
- compact representation
- composition
- corpora
- decision rule
- derivation
- dictionary
- distance measure
- distribution
- document
- english sentence
- error rate
- estimation
- evaluation metric
- finite set
- formalism
- french
- french sentence
- french word
- generation
- hypotheses
- hypothesis
- index
- knowledge
- language processing tasks
- lattice
- lattices
- leaf
- likelihood
- linguistic
- linguistic annotation
- linguistic features
- linguistic knowledge
- linguistic structures
- linguistics
- measure
- measures
- multilingual document
- natural language
- natural language processing tasks
- parse
- parse tree
- parse-tree
- parse-tree syntactic distance
- part-of-speech
- part-of-speech distance
- part-of-speech tags
- phrase
- posterior
- posterior probability
- probabilities
- probability
- probability distribution
- procedure
- process
- processing tasks
- search procedure
- sentence
- sentence pair
- sentences
- statistical models
- statistical translation model
- stress
- symbol
- syntactic distance
- syntactic structure
- system performance
- tags
- term
- terms
- test corpus
- test data
- toolkit
- training
- training and test data
- translation model
- translation models
- translation probabilities
- translation quality
- translations
- tree
- trees
- verb
- vocabulary
- vocabulary size
- word
- word alignments
- word association
- word class distance
- word classes
- word sequences
- words
