ACL RD-TEC 1.0 Summarization of W02-1116
Paper Title:
A MAXIMUM ENTROPY APPROACH TO HOWNET-BASED CHINESE WORD SENSE DISAMBIGUATION
A MAXIMUM ENTROPY APPROACH TO HOWNET-BASED CHINESE WORD SENSE DISAMBIGUATION
Authors: Ping Wai Wong and Yongsheng Yang
Primarily assigned technology terms:
- classification
- database
- databases
- disambiguation
- knowledge bases
- learning
- learning method
- lexical disambiguation
- maxent
- maximum entropy
- maximum entropy approach
- maximum entropy method
- maximum entropy model
- maximum entropy system
- meaning representation
- preprocessing
- pruning
- pruning method
- semantic annotation
- semantic tagging
- sense disambiguation
- sense disambiguation system
- sense pruning
- sense tagger
- sense tagging
- structural disambiguation
- subcategorization
- supervised learning
- tagger
- taggers
- tagging
- word sense disambiguation
Other assigned terms:
- ambiguity
- ambiguity problem
- ambiguous words
- annotation
- approach
- case
- chinese corpora
- chinese corpus
- chinese word
- co-occurrence
- co-occurrence information
- concept
- concepts
- content words
- context information
- contextual information
- corpora
- dependency relation
- dependency relations
- dictionary
- disambiguation system
- entity category
- entity hierarchy
- entropy
- event category
- events
- feature
- function words
- hownet
- hypernym
- information structure
- knowledge
- knowledge base
- large corpus
- lexical entries
- mapping
- mapping table
- maps
- maxent model
- meaning
- meanings
- method
- names
- ontology
- oracle
- part-of-speech
- parts-of-speech
- penn tree bank
- polysemous word
- polysemous words
- pos tag
- precision
- prepositions
- pronoun
- pronouns
- relation
- semantic
- semantic classes
- semantic relations
- semantic tag
- semantic tags
- sense definition
- sense inventory
- sense-tagged corpora
- senses of a word
- sentence
- sentences
- sinica corpus
- sources of information
- suffix
- syntactic structures
- tagged corpus
- tags
- term
- testing corpus
- text
- thesaurus
- tokens
- training
- training corpus
- training data
- tree
- tree bank
- word
- word sense
- word senses
- word types
- wordnet
- words
- xml format