ACL RD-TEC 1.0 Summarization of W04-1122
Paper Title:
AN INTEGRATED METHOD FOR CHINESE UNKNOWN WORD EXTRACTION
AN INTEGRATED METHOD FOR CHINESE UNKNOWN WORD EXTRACTION
Authors: Zhiyong Luo and Rou Song
Primarily assigned technology terms:
- automatic term extraction
- chinese information processing
- chinese term extraction
- chinese unknown word extraction
- chinese word segmentation
- classification
- corpus processing
- dictionary-based method
- disambiguation
- electronic dictionary
- extraction method
- extraction procedure
- hypothesis testing
- identification
- information extraction
- information processing
- information retrieval
- machine translation
- maximum match
- offline corpus processing
- parser
- processing
- recognition
- search
- segmentation
- segmentation system
- segmentor
- syntactic parser
- term extraction
- terms extraction
- text classification
- text-tospeech
- unknown word extraction
- unknown word recognition
- voting
- voting mechanism
- word extraction
- word extraction method
- word recognition
- word segmentation
- word segmentation system
Other assigned terms:
- abbreviations
- ambiguity
- approach
- array
- background corpus
- candidate term
- candidate terms
- characters
- chinese word
- corpora
- data structure
- data structures
- dictionary
- fact
- feature
- hypothesis
- index
- knowledge
- language model
- lexicon
- likelihood
- likelihood ratio
- linguistic
- linguistic knowledge
- linguistic phenomena
- log-likelihood
- log-likelihood ratio
- measure
- measures
- method
- mutual information
- n-gram
- n-grams
- names
- nouns
- organization names
- part-of-speech
- person names
- pointwise mutual information
- precision
- procedure
- relative frequency
- relative frequency ratio
- sentence
- source text
- sparse data
- statistic
- statistics
- style
- substring
- suffix
- symbols
- term
- terms
- test corpus
- text
- word
- word boundary
- words
- writing system
