ACL RD-TEC 1.0 Summarization of P03-2039
Paper Title:
CHINESE UNKNOWN WORD IDENTIFICATION USING CHARACTER-BASED TAGGING AND CHUNKING
CHINESE UNKNOWN WORD IDENTIFICATION USING CHARACTER-BASED TAGGING AND CHUNKING
Authors: Chooi Ling Goh and Masayuki Asahara and Yuji Matsumoto
Primarily assigned technology terms:
- analyzer
- character-based tagging
- chinese unknown word detection
- chinese unknown word identification
- chunker
- chunking
- detection method
- hidden markov
- hidden markov models
- identification
- kernel
- morphological analysis
- morphological analyzer
- morphology
- name extraction
- nlp
- parsing
- person name extraction
- polynomial kernel
- processing
- recognition
- retrieving
- segmentation
- statistical techniques
- support vector machine
- support vector machines
- tagging
- transliteration
- unknown word detection
- unknown word extraction
- unknown word identification
- word detection
- word extraction
- word identification
- words recognition
Other assigned terms:
- approach
- break
- cache
- case
- characters
- chinese language
- chunk
- context window
- corpora
- derivational morphology
- dictionary
- f-measure
- fact
- feature
- japanese language
- kanji
- keyword
- large corpus
- markov models
- method
- morphological rules
- names
- nouns
- open test
- organization names
- parse
- person names
- phrase
- pos sequence
- pos tag
- precision
- probability
- process
- sentence
- statistics
- support vector
- tagged corpora
- tags
- text
- training
- training corpus
- word
- word boundaries
- word tag
- word types
- words
