ACL RD-TEC 1.0 Summarization of W03-1725
Paper Title:
A UNICODE BASED ADAPTIVE SEGMENTOR
A UNICODE BASED ADAPTIVE SEGMENTOR
Authors: Q. Lu and S. T. Chan and R. F. Xu and T. S. Chiu and B. L. Li and S. W. Yu
Primarily assigned technology terms:
- algorithm
- character conversion
- chinese word segmentation
- chinese word segmentor
- dictionary maintenance
- disambiguation
- extractor
- internet
- kernel
- matching
- maximum matching
- maximum-likelihood
- modular design
- part-of-speech tagging
- pre-processing
- processing
- recognition
- segmentation
- segmentation algorithm
- segmentor
- tagging
- word segmentation
- word segmentor
Other assigned terms:
- ambiguity
- annotated corpora
- approach
- canonical form
- case
- characters
- chinese characters
- chinese text
- chinese word
- corpora
- data structure
- dictionaries
- dictionary
- evaluations
- implementation
- knowledge
- knowledge base
- morphological rules
- names
- organization names
- paragraphs
- part-of-speech
- part-of-speech information
- performance evaluation
- personal names
- preprocessor
- process
- proper names
- sentence
- simplified chinese
- statistical data
- statistical information
- statistics
- system design
- testing data
- text
- training
- user
- vocabulary
- word
- words
