ACL RD-TEC 1.0 Summarization of W06-0125
Paper Title:
CHINESE WORD SEGMENTATION AND NAMED ENTITY RECOGNITION BASED ON A CONTEXT-DEPENDENT MUTUAL INFORMATION INDEPENDENCE MODEL
CHINESE WORD SEGMENTATION AND NAMED ENTITY RECOGNITION BASED ON A CONTEXT-DEPENDENT MUTUAL INFORMATION INDEPENDENCE MODEL
Authors: Min Zhang and GuoDong Zhou and LingPeng Yang and DongHong Ji
Primarily assigned technology terms:
- algorithm
- backoff approach
- bracketing
- chinese information processing
- chinese language processing
- chinese named entity recognition
- chinese word segmentation
- chunking
- classification
- classification process
- classifier
- computational linguistics
- decoding
- discriminative modeling
- entity identification
- entity recognition
- entity recognition system
- entropy classifier
- error analysis
- hidden markov
- hidden markov model
- identification
- information processing
- known word segmentation
- language processing
- markov model
- maximum entropy
- maximum entropy classifier
- modeling
- name formation
- name recognition
- named entity identification
- named entity recognition
- ngram modeling
- oov handling
- post-processing
- preprocessing
- processing
- recognition
- recognition system
- segmentation
- segmentation system
- text chunking
- viterbi
- viterbi algorithm
- word bigram
- word generation
- word segmentation
- word segmentation system
Other assigned terms:
- ambiguity
- approach
- association for computational linguistics
- backoff
- bigram
- bigram model
- biomedical domain
- characters
- chinese characters
- chinese language
- chinese text
- chinese word
- chunk
- conditional probability
- conditional probability model
- context information
- corpora
- entity types
- entropy
- f-measure
- fact
- generation
- genre
- independence model
- information independence
- knowledge
- linguistics
- measure
- measures
- method
- mutual information
- mutual information independence
- named entity
- names
- ngram
- nouns
- precision
- probability
- probability model
- process
- scalability
- state transition model
- stress
- text
- training
- training corpus
- unigram
- unigram model
- word
- word bigram model
- word boundaries
- word formation
- word formation pattern
- words
