ACL RD-TEC 1.0 Summarization of P04-1036
Paper Title:
FINDING PREDOMINANT WORD SENSES IN UNTAGGED TEXT
FINDING PREDOMINANT WORD SENSES IN UNTAGGED TEXT
Authors: Diana McCarthy and Rob Koeling and Julie Weeds and John Carroll
Primarily assigned technology terms:
Other assigned terms:
- approach
- british english
- brown corpus
- co-occurrence
- concepts
- contextual features
- corpora
- dictionary
- distance measure
- distribution
- distributional similarity
- english language
- experimental results
- fact
- frequency counts
- frequency distribution
- genre
- germanet
- grammatical relation
- grammatical relations
- hand-tagged corpora
- heuristic
- hierarchical structure
- hyponymy
- hyponymy relation
- information content
- labeling
- lexical resources
- mapping
- meaning
- measure
- measures
- method
- nouns
- parsed corpus
- penn treebank
- penn treebank ii
- precision
- prior distribution
- procedure
- random sample
- relation
- reuters corpus
- semantic
- semantic relatedness
- semantic similarity
- semantic similarity measure
- semcor
- sense distinctions
- sense inventory
- senses of a word
- similarity measure
- similarity measures
- similarity score
- similarity scores
- subcategorisation
- synonyms
- synset
- synsets
- syntactic evidence
- target word
- technique
- technologies
- term
- test data
- text
- text type
- textbook
- textual corpora
- thesaurus
- topics
- training
- training data
- treebank
- untagged text
- verb
- verb classes
- word
- word sense
- word senses
- word-net
- wordnet
- wordnet hierarchy
- wordnet sense
- wordnet senses
- wordnet similarity
- wordnet synsets
- words
