ACL RD-TEC 1.0 Summarization of W03-1705
Paper Title:
A BOTTOM-UP MERGING ALGORITHM FOR CHINESE UNKNOWN WORD EXTRACTION
A BOTTOM-UP MERGING ALGORITHM FOR CHINESE UNKNOWN WORD EXTRACTION
Authors: Wei-Yun Ma and Keh-Jiann Chen
Primarily assigned technology terms:
- algorithm
- bottom-up merging
- chinese unknown word extraction
- chinese word segmentation
- corpus-based learning
- decision making
- detection method
- disambiguation
- disambiguation process
- extraction system
- greedy algorithm
- information processing
- internet
- learning
- learning algorithm
- matching
- modeling
- modelling
- processing
- ranking
- rule matching
- segmentation
- segmentation process
- statistical methods
- support vector machine
- unknown word detection
- unknown word extraction
- unsupervised segmentation
- word detection
- word extraction
- word extraction system
- word segmentation
Other assigned terms:
- adjective
- ambiguity
- ambiguity problem
- approach
- association strength
- characters
- chinese characters
- chinese text
- chinese word
- chinese words
- co-occurrence
- compounds
- conditional probability
- context free grammar
- data sets
- derivation
- detection rate
- dice
- document
- entropy
- experimental results
- extraction process
- foreign word
- frame
- generative grammar
- grammar
- grammars
- input text
- lexicon
- linguistic
- matching process
- measure
- measures
- method
- morpheme
- morphemes
- morphological rules
- mutual information
- names
- non-terminal symbol
- precision
- preposition
- probability
- procedure
- process
- right-hand side
- rule set
- semantic
- semantic relations
- sentence
- sentences
- statistical measure
- suffix
- support vector
- symbol
- symbols
- syntactic categories
- syntactic constraints
- terms
- testing data
- testing set
- text
- tokens
- training
- training corpus
- training set
- unknown word morpheme
- verb
- word
- word structure
- word types
- words
