ACL RD-TEC 1.0 Summarization of C04-1177
Paper Title:
AUTOMATIC IDENTIFICATION OF INFREQUENT WORD SENSES
AUTOMATIC IDENTIFICATION OF INFREQUENT WORD SENSES
Authors: Diana McCarthy and Rob Koeling and Julie Weeds and John Carroll
Primarily assigned technology terms:
- clustering
- disambiguation
- identification
- information retrieval
- lexical acquisition
- nearest neighbors
- nlp
- parser
- parsing
- ranking
- ranking method
- scoring
- sense disambiguation
- sense ranking
- statistical parsing
- thesaurus construction
- unsupervised method
- word sense disambiguation
- wordnet similarity package
Other assigned terms:
- ambiguity
- approach
- brown corpus
- cluster
- co-occurrence
- concepts
- corpora
- distance measure
- distribution
- distributional similarity
- domain-specific corpora
- english language
- experimental results
- frequency counts
- frequency distribution
- germanet
- grammatical relation
- heuristic
- hierarchical structure
- hyponymy
- hyponymy relation
- information content
- lexical resources
- meaning
- measure
- measures
- method
- nlp applications
- nouns
- precision
- prior distribution
- procedure
- process
- relation
- relative frequency
- reuters corpus
- semantic
- semantic similarity
- semantic similarity measure
- semcor
- sense ambiguity
- sense inventory
- senses of a word
- similarity measure
- similarity measures
- similarity score
- similarity scores
- synset
- synsets
- syntactic evidence
- target word
- technique
- technologies
- term
- test corpora
- test data
- text
- text type
- thesaurus
- tokens
- topics
- training
- training data
- tree
- verb
- verb senses
- word
- word sense
- word sense ambiguity
- word senses
- word-net
- wordnet
- wordnet hierarchy
- wordnet senses
- wordnet similarity
- wordnet synsets
- words
