ACL RD-TEC 1.0 Summarization of P04-1038
Paper Title:
CHINESE VERB SENSE DISCRIMINATION USING AN EM CLUSTERING MODEL WITH RICH LINGUISTIC FEATURES
CHINESE VERB SENSE DISCRIMINATION USING AN EM CLUSTERING MODEL WITH RICH LINGUISTIC FEATURES
Authors: Jinying Chen and Martha Palmer
Primarily assigned technology terms:
- algorithm
- bootstrapping
- bootstrapping approach
- classification
- classifier
- clustering
- clustering algorithm
- co-reference resolution
- disambiguation
- document retrieval
- expectation-maximization
- feature selection
- grouping
- information access
- information extraction
- learning
- learning algorithm
- machine learning
- machine learning algorithm
- machine translation
- mapping algorithm
- maximum entropy
- nlp
- parser
- parsing
- pos tagging
- preprocessing
- reading
- relation detection
- search
- searching
- segmentation
- sense disambiguation
- sense discrimination
- tagging
- unsupervised learning
- word sense classifier
- word sense disambiguation
- word sense discrimination
Other assigned terms:
- ambiguous words
- annotated corpora
- approach
- case
- chinese nouns
- chinese treebank
- classification accuracy
- cluster
- clustering model
- clusters
- co-occurrence
- co-reference
- coherence
- compounds
- conditional probability
- contextual information
- corpora
- corpus evidence
- dictionaries
- dictionary
- dictionary entries
- distribution
- document
- english verbs
- entropy
- experimental results
- external knowledge
- fact
- feature
- feature set
- hownet
- implementation
- joint probability
- knowledge
- labeling
- lexical choice
- lexical features
- lexical set
- lexicon
- linguistic
- linguistic features
- mapping
- mappings
- meaning
- meanings
- measure
- measures
- modern chinese-english dictionary
- mutual information
- nlp tasks
- nouns
- opinions
- parsing information
- particle
- parts of speech
- penn chinese treebank
- perplexity
- polysemous words
- pos tag
- predicate-argument
- predicate-argument structure
- preposition
- probabilistic model
- probability
- relation
- seed
- seed words
- semantic
- semantic categories
- semantic category
- semantic classes
- semantic features
- semantic taxonomy
- sense distinctions
- sense-tagged corpora
- sense-tagged corpus
- sentence
- sentences
- sentential complements
- sparse data
- standard deviation
- tags
- target verb
- taxonomy
- test data
- text
- training
- training and test data
- training data
- treebank
- unannotated corpora
- unannotated corpus
- unannotated text
- verb
- verb sense
- verb senses
- word
- word sense
- wordnet
- words
- wsd model
