ACL RD-TEC 1.0 Summarization of I05-3020
Paper Title:
REPORT TO BMM-BASED CHINESE WORD SEGMENTOR WITH CONTEXT-BASED UNKNOWN WORD IDENTIFIER FOR THE SECOND INTERNATIONAL CHINESE WORD SEGMENTATION BAKEOFF
REPORT TO BMM-BASED CHINESE WORD SEGMENTOR WITH CONTEXT-BASED UNKNOWN WORD IDENTIFIER FOR THE SECOND INTERNATIONAL CHINESE WORD SEGMENTATION BAKEOFF
Primarily assigned technology terms:
- algorithm
- chinese natural language processing
- chinese word segmentation
- chinese word segmentor
- disambiguation
- language processing
- matching
- maximum matching
- mining
- morphology
- natural language processing
- nlp
- optimization
- pre-processing
- processing
- recognition
- search
- search engines
- segmentation
- segmentor
- speech recognition
- statistical approaches
- text mining
- word bigram
- word segmentation
- word segmentation bakeoff
- word segmentor
Other assigned terms:
- ambiguity
- bigram
- case
- characters
- chinese corpus
- chinese sentence
- chinese word
- dictionary
- f-measure
- knowledge
- linguistic
- linguistic knowledge
- luw-eiw tradeoff
- natural language
- part-ofspeech
- probabilities
- probability
- process
- segmentation bakeoff
- sentence
- simplified chinese
- tags
- technique
- testing corpus
- text
- training
- training corpus
- web corpus
- word
- word segmentation performance
- word types
- words
