ACL RD-TEC 1.0 Summarization of W03-1718
Paper Title:
SINGLE CHARACTER CHINESE NAMED ENTITY RECOGNITION
SINGLE CHARACTER CHINESE NAMED ENTITY RECOGNITION
Authors: Xiaodan Zhu and Mu Li and Jianfeng Gao and Chang-Ning Huang
Primarily assigned technology terms:
- algorithm
- binary classification
- chinese named entity recognition
- chinese parser
- chinese word segmentation
- classification
- classifier
- classifiers
- disambiguation
- english ner
- entity recognition
- error analysis
- human checking
- iterative scaling
- maximum entropy
- maximum entropy model
- message understanding
- name recognition
- named entity recognition
- ner evaluation
- normalization
- parser
- person name recognition
- recognition
- recognizer
- search
- segmentation
- tagging
- term weighting
- tf-idf weighting
- training algorithm
- vector space model
- viterbi
- viterbi search
- weighting
- word breaking
- word segmentation
Other assigned terms:
- abbreviation
- ambiguity
- annotators
- approach
- binary classification problem
- case
- characters
- chinese sentence
- chinese text
- chinese word
- chinese words
- classification problem
- classification task
- coefficient
- concept
- concepts
- conditional probability
- context features
- context model
- context window
- corpora
- development set
- dictionaries
- dictionary
- distribution
- entropy
- evaluation methodology
- evaluation metrics
- experimental results
- f-score
- feature
- feature set
- heuristic
- heuristic rules
- input string
- japanese ne
- knowledge
- language model
- large corpus
- lattice
- lexicon
- linguistic
- linguistic constraints
- linguistic knowledge
- linguists
- local context
- location name
- log-linear model
- maximum entropy principle
- measure
- message
- message understanding conference
- method
- methodology
- model probability
- n-gram
- n-gram models
- name entity
- named entities
- named entity
- names
- normalization factor
- person names
- phrase
- precision
- probabilities
- probability
- probability distribution
- procedure
- recognition task
- sentence
- single character location
- source-channel model
- statistical models
- statistics
- substring
- syntactic structure
- tags
- technique
- technologies
- term
- terms
- test corpus
- test data
- test set
- text
- time expressions
- tokens
- training
- training corpus
- training data
- understanding
- uniform distribution
- vector space
- window size
- word
- word classes
- word definition
- word segmentation performance
- words
