ACL RD-TEC 1.0 Summarization of P06-1058
Paper Title:
AN EQUIVALENT PSEUDOWORD SOLUTION TO CHINESE WORD SENSE DISAMBIGUATION
AN EQUIVALENT PSEUDOWORD SOLUTION TO CHINESE WORD SENSE DISAMBIGUATION
Authors: Zhimao Lu and Haifeng Wang and Jianmin Yao and Ting Liu and Sheng Li
Primarily assigned technology terms:
- algorithm
- automatic generation
- automatic text summarization
- bayesian classifier
- bayesian modeling
- bootstrapping
- classification
- classifier
- classifier construction
- clustering
- computational linguistics
- computing
- corpus alignment
- corpus tagging
- database
- decision tree
- disambiguation
- feature selection
- genetic algorithms
- information retrieval
- internet
- knowledge acquisition
- language processing
- learning
- learning method
- learning methods
- machine learning
- machine learning methods
- machine translation
- mathematical modeling
- maximum entropy
- mining
- model training
- modeling
- naive bayesian
- natural language processing
- neural network
- processing
- reasoning
- search
- semantic analysis
- semantic knowledge acquisition
- semi-supervised learning
- sense disambiguation
- sense tagging
- statistical learning
- summarization
- supervised learning
- supervised method
- tagging
- text classification
- text mining
- text summarization
- unsupervised algorithm
- unsupervised learning
- unsupervised learning method
- unsupervised method
- unsupervised wsd
- weakly supervised learning
- word sense disambiguation
- wsd model training
Other assigned terms:
- ambiguous word
- ambiguous words
- approach
- association for computational linguistics
- bayesian model
- bilingual corpus
- chinese language
- chinese word
- cluster
- co-occurrence
- concept
- conditional probability
- content words
- context window
- context words
- contextual word
- corpora
- data set
- data sparseness
- dictionary
- disambiguation task
- entropy
- evaluation method
- experimental results
- f-measure
- feature
- generation
- gold standard
- human intervention
- implementation
- knowledge
- knowledge acquisition bottleneck
- large corpus
- leaf
- linguistic
- linguistic knowledge
- linguistic resources
- linguistics
- machine-readable dictionary
- maps
- maximum similarity
- meaning
- method
- monolingual corpus
- morpheme
- morphemes
- natural language
- nouns
- occurrence probability
- open test
- parallel corpora
- parallel corpus
- polysemous words
- pragmatic information
- precision
- priori
- probability
- process
- root node
- seed
- semantic
- semantic and pragmatic
- semantic distance
- semantic information
- semantic knowledge
- semantic synonym
- sense inventory
- sense similarity
- sentence
- statistical information
- statistical model
- statistics
- synonym
- synonyms
- syntax
- syntax and semantics
- tagged corpus
- tags
- technique
- technologies
- technology
- test set
- testing set
- text
- thesaurus
- training
- training corpus
- training data
- training set
- tree
- tree structure
- word
- word sense
- wordaligned corpus
- words
- wsd model
