ACL RD-TEC 1.0 Summarization of W96-0104
Paper Title:
LEARNING SIMILARITY-BASED WORD SENSE DISAMBIGUATION FROM SPARSE DATA
LEARNING SIMILARITY-BASED WORD SENSE DISAMBIGUATION FROM SPARSE DATA
Authors: Yael Karov and Shimon Edelman
Primarily assigned technology terms:
Other assigned terms:
- ambiguous word
- approach
- bias
- bilingual corpora
- bilingual corpus
- bilingual lexicon
- british national corpus
- cluster
- clusters
- context similarity
- context words
- contextual similarity
- corpora
- dictionaries
- dictionary
- dictionary definition
- dictionary definitions
- disambiguation task
- discourse
- estimation
- feature
- feature space
- knowledge
- knowledge acquisition bottleneck
- large corpus
- lexicon
- likelihood
- machine-readable dictionary
- manual intervention
- manual translation
- maps
- measure
- measures
- method
- monolingual corpus
- nouns
- part of speech
- polysemous word
- polysemous words
- probability
- process
- seed
- semantic
- semantic similarity
- sense distinctions
- sense information
- senses of a word
- sentence
- sentence similarity
- sentences
- similarity matrix
- similarity measure
- similarity measures
- sparse data
- statistics
- tags
- target word
- text
- text corpora
- text corpus
- thesaurus
- training
- training corpus
- training data
- training set
- translations
- word
- word sense
- word similarity
- wordnet
- words
