ACL RD-TEC 1.0 Summarization of C02-1143
Paper Title:
SIMPLE FEATURES FOR CHINESE WORD SENSE DISAMBIGUATION
SIMPLE FEATURES FOR CHINESE WORD SENSE DISAMBIGUATION
Authors: Hoa Trang Dang and Ching-yi Chia and Martha Palmer and Fu-Dong Chiou
Primarily assigned technology terms:
- 5-fold cross validation
- algorithm
- automatic named entity tagger
- automatic segmentation
- boundary detection
- bracketing
- chinese bracketing
- chinese word segmentation
- chinese-english machine translation
- chinese-english translation
- classification
- collins parser
- cross validation
- disambiguation
- document retrieval
- english wsd
- entity tagger
- feature extraction
- information retrieval
- information retrieval systems
- language processing
- learning
- linguistic processing
- machine translation
- machine translation systems
- maximum entropy
- maximum entropy approach
- maximum entropy framework
- maximum entropy model
- maximum entropy system
- named entity tagger
- natural language processing
- nlp
- parser
- parsing
- part-of-speech tagger
- part-of-speech tagging
- partitioning
- preprocessing
- processing
- retrieval systems
- sampling
- scoring
- segmentation
- sense disambiguation
- sense tagging
- sense-tagging
- sentence boundary detection
- supervised training
- tag-based parser
- tagger
- tagging
- translation systems
- validation
- word segmentation
- word sense disambiguation
Other assigned terms:
- ambiguity
- ambiguous words
- analogy
- annotation
- annotators
- approach
- case
- chinese corpora
- chinese lexical
- chinese treebank
- chinese word
- chinese words
- class information
- classification task
- collocational information
- conceptual structures
- conditional probability
- contextual features
- corpora
- ctb corpus
- dictionaries
- dictionary
- dictionary entry
- distribution
- document
- english verb
- english verbs
- entropy
- entropy models
- evaluation data
- experimental results
- fact
- feature
- feature sets
- feature weights
- frame
- gold standard
- head word
- hownet
- keyword
- knowledge
- lemma
- lexical choice
- lexical level
- lexicon
- linguistic
- linguistic annotation
- linguistic features
- linguistic knowledge
- manual segmentation
- maximum entropy models
- method
- named entity
- natural language
- nlp applications
- nlp tasks
- noise
- noun category
- nouns
- ontology
- parse
- part of speech
- part-of-speech
- part-of-speech tags
- parts of speech
- passivization
- penn chinese treebank
- phrase
- precision
- predicate-argument
- prepositions
- probability
- probability distribution
- selectional restrictions
- semantic
- semantic class
- semantic class information
- semantic classes
- semantic features
- sentence
- sentence boundary
- sentences
- standard deviation
- style
- syntactic features
- system performance
- tags
- target word
- test data
- text
- training
- training and test data
- training data
- transformation
- translations
- treebank
- verb
- verb arguments
- verb sense
- verb senses
- vocabulary
- word
- word sense
- wordnet
- wordnet class
- words
