ACL RD-TEC 1.0 Summarization of J94-4003
Paper Title:
WORD SENSE DISAMBIGUATION USING A SECOND LANGUAGE MONOLINGUAL CORPUS
WORD SENSE DISAMBIGUATION USING A SECOND LANGUAGE MONOLINGUAL CORPUS
Authors: Ido Dagan and Alon Itai
Primarily assigned technology terms:
- algorithm
- approximation
- bayesian classifier
- bidirectional translation
- bootstrapping
- bootstrapping approach
- character recognition
- classification
- classifier
- clustering
- coding
- comparative analysis
- computational linguistics
- computer science
- computing
- constraint propagation
- constraint propagation algorithm
- correction method
- database
- databases
- decomposition
- deep understanding
- disambiguating prepositional phrase
- disambiguation
- disambiguation method
- estimation method
- estimator
- frequencies method
- full parsing
- identification
- language modeling
- language parser
- language processing
- likelihood estimator
- machine translation
- machine translation system
- machine translation systems
- maximum likelihood
- maximum likelihood estimator
- modeling
- n-gram language modeling
- natural language processing
- one-to-one mapping
- optical character recognition
- optimization
- parser
- parsers
- parsing
- partial parsing
- postprocessing
- preprocessing
- processing
- propagation algorithm
- random selection
- reading
- recognition
- reporting
- selection algorithm
- selection method
- sense disambiguation
- sense selection
- similarity-based estimation
- singular value decomposition
- speech recognition
- speech tagger
- statistical approaches
- statistical language processing
- statistical machine translation
- statistical machine translation system
- statistical methods
- statistical sense disambiguation
- subcategorization
- syntactic analysis
- syntactic parser
- syntactic parsing
- tagger
- taggers
- tagging
- target word selection
- terminology
- training method
- translation process
- translation system
- translation systems
- translator
- tuning
- weighting
- word classification
- word frequencies method
- word selection
- word sense disambiguation
Other assigned terms:
- adjective
- aligned corpus
- ambiguity
- ambiguous word
- ambiguous words
- approach
- association for computational linguistics
- benchmark
- bilingual corpora
- bilingual corpus
- bilingual lexicon
- case
- cluster
- clusters
- co-occurrence
- co-occurrence information
- co-occurrence statistics
- co-occurrences
- coefficient
- compounds
- concept
- concepts
- conditional probabilities
- content words
- context vector
- context vectors
- context words
- corpora
- corpus size
- correlation
- data sets
- data sparseness
- data structure
- decision theory
- device
- dictionary
- disambiguation model
- discourse
- distance metric
- distribution
- domain-specific terminology
- electronic form
- english corpus
- english sentence
- english translation
- estimation
- evaluation method
- evaluations
- events
- experimental results
- experimental setting
- fact
- finite set
- formalisms
- frame
- french
- french sentence
- frequency counts
- function words
- generation
- grammars
- hansard corpus
- head noun
- hebrew corpus
- heuristics
- hypotheses
- hypothesis
- implementation
- index
- information sources
- interpolation
- interpretation
- knowledge
- language corpora
- language corpus
- language information
- language model
- language models
- language pairs
- language processing tasks
- large corpora
- large corpus
- lexical ambiguity
- lexical co-occurrence
- lexical items
- lexical relation
- lexical relations
- lexicon
- likelihood
- linguistic
- linguistic data
- linguistic information
- linguistic model
- linguistic phenomena
- linguistic structures
- linguistic theories
- linguistics
- local context
- manual tagging
- manual translation
- mapping
- mappings
- maps
- meaning
- measure
- method
- monolingual corpora
- monolingual corpus
- multinomial distribution
- multinomial model
- n-gram
- n-gram model
- n-gram models
- names
- natural language
- natural language processing tasks
- noise
- normal distribution
- nouns
- null hypothesis
- opinion
- paragraphs
- parallel bilingual corpus
- parse
- parse time
- parsed corpus
- part of speech
- parts of speech
- performance evaluation
- phrase
- phrase attachment
- possible translation
- pragmatic knowledge
- precision
- preposition
- prepositional phrase
- prepositional phrase attachment
- prepositional phrases
- prepositions
- priori
- probabilistic model
- probabilities
- probability
- procedure
- process
- processing tasks
- pronoun
- psycholinguistic research
- quantitative information
- relation
- relative clauses
- relative frequency
- representations
- research and development
- right-hand side
- semantic
- semantic categories
- semantic constraint
- semantic knowledge
- sense disambiguation model
- sense distinction
- sense distinctions
- senses of a word
- sentence
- sentences
- similarity between words
- slot
- slot grammars
- source language
- source language sentence
- source language word
- source sentence
- sources of information
- statistical data
- statistical decision theory
- statistical information
- statistical model
- statistical models
- statistical significance
- statistics
- subcategorization frame
- subcategorization frames
- syntactic behavior
- syntactic categories
- syntactic context
- syntactic function
- syntactic relation
- syntactic relations
- syntactic rules
- syntactic theory
- tagged corpus
- target language
- target language corpus
- target language model
- target languages
- target word
- technology
- term
- terms
- test data
- test set
- testing set
- text
- theories
- theory
- thesaurus
- tokens
- topics
- training
- training corpora
- training corpus
- training examples
- training phase
- transfer model
- transformation
- transformation rules
- translation probabilities
- translations
- understanding
- untagged corpus
- verb
- word
- word classes
- word co-occurrence
- word frequencies
- word frequency
- word level
- word order
- word sense
- word senses
- words
