ACL RD-TEC 1.0 Summarization of I05-3026
Paper Title:
DESCRIPTION OF THE HKU CHINESE WORD SEGMENTATION SYSTEM FOR SIGHAN BAKEOFF 2005
DESCRIPTION OF THE HKU CHINESE WORD SEGMENTATION SYSTEM FOR SIGHAN BAKEOFF 2005
Authors: Guohong Fu and Kang-Kwong Luke and Percy Ping-Wai WONG
Primarily assigned technology terms:
- chinese text processing
- chinese word segmentation
- disambiguation
- hmm tagger
- identification
- known word segmentation
- processing
- segmentation
- segmentation system
- tagger
- tagging
- text processing
- unknown word identification
- word bigram
- word identification
- word segmentation
- word segmentation bakeoff
- word segmentation system
Other assigned terms:
- ambiguous segmentation
- bigram
- bigram model
- characters
- chinese characters
- chinese text
- chinese word
- chinese words
- corpora
- dictionaries
- dictionary
- f measure
- f-measure
- grammar
- lexicon
- measure
- measures
- open test
- out-of-vocabulary rate
- part-of-speech
- part-of-speech information
- pfr corpus
- precision
- probability
- process
- segmentation bakeoff
- sentence
- sinica corpus
- tagging task
- tags
- technology
- test corpus
- testing corpora
- text
- training
- training corpora
- training corpus
- training data
- word
- word bigram model
- word boundaries
- words
