ACL RD-TEC 1.0 Summarization of P94-1013
Paper Title:
DECISION LISTS FOR LEXICAL AMBIGUITY RESOLUTION: APPLICATION TO ACCENT RESTORATION IN SPANISH AND FRENCH
DECISION LISTS FOR LEXICAL AMBIGUITY RESOLUTION: APPLICATION TO ACCENT RESTORATION IN SPANISH AND FRENCH
Primarily assigned technology terms:
- accent restoration
- algorithm
- ambiguity resolution
- analyzer
- approximation
- automatic evaluation
- bayesian classifier
- capitalization
- capitalization restoration
- classification
- classifier
- classifiers
- corpus analysis
- cross-validation
- decision list algorithm
- decision tree
- decision trees
- disambiguation
- homograph disambiguation
- homograph resolution
- homophone disambiguation
- learning
- learning algorithms
- lemmatization
- lexical ambiguity resolution
- lexical disambiguation
- list algorithm
- machine learning
- machine learning algorithms
- machine translation
- matching
- measuring
- modeling
- morphological analysis
- morphological analyzer
- nlp
- nlp systems
- objective evaluation
- parallelization
- parsers
- part-of-speech tagger
- part-of-speech tagging
- phonetic analysis
- prolog
- pruning
- pruning strategy
- ranking
- right-branching
- semantic ambiguity resolution
- sense-disambiguation
- smoothing
- speech synthesis
- speech tagger
- spelling
- synthesis
- tagger
- taggers
- tagging
- text-to-speech
- text-to-speech synthesis
- translators
- word-sense disambiguation
Other assigned terms:
- accent
- adjective
- agreement rate
- ambiguity
- ambiguous word
- ambiguous words
- approach
- baseline performance
- bayesian decision theory
- bigram
- case
- classification performance
- classification tasks
- clusters
- collocation
- collocational information
- comparative study
- concepts
- concordance
- corpora
- data set
- decision theory
- dictionaries
- disambiguation task
- distribution
- error rate
- feature
- feature set
- formal model
- formalisms
- french
- french text
- frequency distribution
- gender agreement
- grammar
- hebrew text
- heuristics
- histogram
- implementation
- inflected form
- inflected forms
- interpolation
- knowledge
- language resources
- large training
- lexical ambiguity
- lexical resources
- lexicon
- likelihood
- likelihood ratio
- linguistic
- linguistic knowledge
- linguistics
- linguistics research
- log-likelihood
- log-likelihood ratio
- meaning
- measure
- measures
- mood
- n-gram
- noise
- nouns
- number agreement
- part of speech
- part-of-speech
- part-of-speech information
- part-of-speech tag
- part-of-speech tags
- parts of speech
- parts-of-speech
- precision
- probabilities
- probability
- probability distribution
- probability distributions
- probability estimate
- procedure
- process
- recipe
- relative frequency
- run-time
- selectional constraints
- semantic
- semantic ambiguity
- semantic evidence
- semantic information
- sentences
- sparse data
- statistics
- subsumption
- suffixes
- syntactic ambiguity
- syntactic constraints
- syntactic evidence
- syntactic patterns
- tagged corpora
- tags
- target word
- technique
- term
- test data
- test material
- text
- text corpora
- theory
- thesaurus
- tokens
- training
- training and test data
- training corpora
- training corpus
- training data
- training phase
- training set
- tree
- trees
- word
- word choice
- word classes
- words