ACL RD-TEC 1.0 Summarization of C92-2070
Paper Title:
WORD-SENSE DISAMBIGUATION USING STATISTICAL MODELS OF ROGET'S CATEGORIES TRAINED ON LARGE CORPORA
WORD-SENSE DISAMBIGUATION USING STATISTICAL MODELS OF ROGET'S CATEGORIES TRAINED ON LARGE CORPORA
Primarily assigned technology terms:
- algorithm
- bayesian discrimination
- bilingual lexicography
- bootstrapping
- classification
- computational linguistics
- disambiguation
- editing
- information retrieval
- knowledge acquisition
- linking
- machine translation
- processing
- recognizer
- search
- sense disambignation
- sense disambiguation
- speech processing
- speech synthesis
- statistical approaches
- synthesis
- table lookup
- tagging
- tense classification
- tile
- topic classification
- weighting
- word sense disambiguation
Other assigned terms:
- ambiguity
- ambiguous word
- approach
- bilingual corpora
- bilingual corpus
- bilingual text
- case
- clusters
- community
- concept
- concordance
- context models
- corpora
- correlations
- device
- dictionaries
- dictionary
- dictionary definition
- dimensionality
- encyclopedia
- entropy
- expository convenience
- french
- human intervention
- human involvement
- idiom
- implementation
- index
- knowledge
- knowledge acquisition bottleneck
- lexicography
- lexicon
- linguistics
- local context
- machine readable dictionaries
- method
- names
- noise
- nominals
- nouns
- parallel bilingual corpus
- part of speech
- phrase
- polysemous word
- polysemous words
- polysemy
- precision
- probabilities
- probability
- procedure
- process
- representations
- sense distinction
- sense distinctions
- senses of a word
- sentence
- signal
- statistical model
- statistical models
- system performance
- tags
- terms
- test corpus
- test set
- text
- text corpora
- theoretical framework
- thesaurus
- training
- training corpus
- training examples
- training material
- training set
- translations
- vocabulary
- window size
- word
- word classes
- word sense
- word senses
- words
