ACL RD-TEC 1.0 Summarization of W06-0112
Paper Title:
A HYBRID APPROACH TO CHINESE BASE NOUN PHRASE CHUNKING
A HYBRID APPROACH TO CHINESE BASE NOUN PHRASE CHUNKING
Authors: Fang Xu and Chengqing Zong and Jun Zhao
Primarily assigned technology terms:
- algorithm
- binary classifier
- bracketing
- chinese language processing
- chunker
- chunking
- classification
- classifier
- classifier training
- classifiers
- computational linguistics
- conditional random field
- conditional random fields
- cross validation
- data representation
- entity extraction
- error-pruning method
- feature selection
- forward-backward algorithm
- identification
- information extraction
- information retrieval
- kernel
- language processing
- learning
- learning algorithm
- learning method
- learning methods
- likelihood training
- machine learning
- machine learning algorithm
- machine learning methods
- matching
- maximum entropy
- maximum entropy method
- maximum likelihood
- maximum likelihood training
- memory-based learning
- model construction
- multi-class classification
- name entity extraction
- natural language processing
- normalization
- noun phrase chunking
- np chunker
- np chunking
- np identification
- parsing
- phrase chunking
- polynomial kernel
- post-processing
- processing
- pruning
- recognition
- recognition procedure
- scoring
- scoring method
- segmentation
- semisupervised learning
- sequence labeling
- shallow parsing
- statistical methods
- statistical techniques
- structural learning
- summarization
- support vector machine
- support vector machines
- syntactic bracketing
- tagging
- text processing
- text summarization
- transformation-based learning
- validation
- voting
Other assigned terms:
- adjective
- adverb
- ambiguity
- ambiguous words
- approach
- association for computational linguistics
- base noun
- base noun phrase
- case
- characters
- chinese characters
- chinese language
- chinese sentence
- chinese treebank
- chinese word
- chinese words
- chunk
- chunks
- classification problem
- complex noun
- conditional probabilities
- conditional probability
- data set
- data sets
- distribution
- entropy
- evaluation metrics
- experimental results
- f-score
- feature
- feature sets
- grammar
- grammar rules
- grammars
- heuristic
- heuristics
- intention
- joint distribution
- knowledge
- labeling
- language processing tasks
- lexical information
- likelihood
- linguistics
- log-likelihood
- mapping
- meanings
- measure
- method
- multi-class classification problem
- name entity
- natural language
- natural language processing tasks
- noise
- normalization factor
- noun phrase
- noun phrases
- nouns
- part-of-speech
- penn chinese treebank
- phoneme
- phrase
- precision
- preposition
- probabilistic models
- probabilities
- probability
- procedure
- process
- processing tasks
- proper noun
- representations
- segments
- semantic
- sentence
- sentences
- statistics
- support vector
- svms
- syntactic structure
- tagging problem
- tags
- technology
- termination criterion
- test corpus
- test data
- testing data
- text
- tokens
- training
- training and testing data
- training corpus
- training data
- training data set
- transition matrix
- treebank
- word
- words
