ACL RD-TEC 1.0 Summarization of W97-0213
Paper Title:
A PERSPECTIVE ON WORD SENSE DISAMBIGUATION METHODS AND THEIR EVALUATION
A PERSPECTIVE ON WORD SENSE DISAMBIGUATION METHODS AND THEIR EVALUATION
Primarily assigned technology terms:
- algorithm
- anaphora resolution
- broad-coverage sense tagging
- classification
- classifier
- computing
- concordance tool
- cross-validation
- data annotation
- disambiguation
- disambiguation algorithm
- information retrieval
- ir system
- language processing
- learning
- learning algorithms
- linking
- machine translation
- machine-translation
- natural language processing
- noisy channel model
- parsers
- parsing
- part-of-speech tagging
- processing
- random selection
- recognition
- recognizer
- sense disambiguation
- sense disambiguation algorithm
- sense tagger
- sense tagging
- sequential tagging
- smoothing
- speech recognition
- speech recognizer
- speech synthesis
- supervised learning
- supervised training
- synthesis
- system development and evaluation
- tagger
- taggers
- tagging
- topic classifier
- translators
- unsupervised sense disambiguation
- unsupervised tagging
- weighting
- word sense disambiguation
Other assigned terms:
- aligned corpus
- ambiguity
- ambiguous word
- ambiguous words
- anaphora
- annotated corpora
- annotation
- annotation effort
- annotator
- annotators
- approach
- bias
- bilingual corpora
- bilingual corpus
- bilingual dictionaries
- brown corpus
- case
- clusters
- community
- concordance
- corpora
- cross entropy
- data set
- data sets
- dictionaries
- dictionary
- disambiguating word
- distance matrix
- distribution
- document
- dutch
- english vocabulary
- entropy
- evaluation data
- evaluation measure
- evaluation methodology
- evaluation metrics
- evaluation paradigm
- evaluations
- exact match
- french
- generation
- human annotator
- inter-annotator agreement
- kullback-leibler distance
- language models
- language processing tasks
- large corpora
- large training
- ldoce
- lexical information
- lexical resources
- lexical semantics
- manual annotation
- maps
- meaning
- meanings
- measure
- measures
- methodology
- natural language
- natural language processing tasks
- noisy channel
- parallel corpora
- parallel corpus
- part of speech
- part-of-speech
- parts of speech
- penn treebank
- perplexity
- polysemous word
- polysemous words
- polysemy
- probabilities
- probability
- probability distribution
- probability estimate
- probability estimates
- process
- processing tasks
- pronunciation
- query
- regular polysemy
- representations
- scalability
- segments
- semantic
- semantic concordance
- semantic hierarchy
- sense ambiguity
- sense distinction
- sense distinctions
- sense information
- sense inventory
- sentence
- sources of information
- sparse data
- statistics
- subcorpus
- synonyms
- synsets
- system development
- tag set
- tagged corpus
- tagging research
- tags
- target language
- target languages
- target word
- term
- terms
- test corpus
- test data
- test set
- text
- tokens
- training
- training and test data
- training data
- training set
- treebank
- unannotated corpus
- unannotated text
- verb
- verb senses
- vocabulary
- word
- word sense
- word senses
- wordnet
- wordnet synsets
- words
- wsd evaluation
