ACL RD-TEC 1.0 Summarization of W03-1729
Paper Title:
SYSTRAN'S CHINESE WORD SEGMENTATION
SYSTRAN'S CHINESE WORD SEGMENTATION
Authors: Jin Yang and Jean Senellart and Remi Zajac
Primarily assigned technology terms:
- algorithm
- automaton
- character matching
- chinese segmentation
- chinese word segmentation
- chinese-english machine translation
- chinese-english mt
- database
- dictionary lookup
- disambiguation
- encoding
- entity recognition
- entity recognizer
- evaluation process
- extraction tool
- finite state
- finite state automaton
- finite-state technology
- identification
- japanese segmentation
- machine translation
- machine translation system
- matching
- mt engine
- mt system
- name entity recognition
- name entity recognizer
- name recognition
- preprocessing
- processing
- processor
- ranking
- recognition
- recognizer
- regression
- regression testing
- rule matching
- rule-based approach
- segmentation
- segmenter
- state automaton
- terminology
- terminology extraction
- training process
- translation system
- unknown word identification
- unknown word processing
- unknown word recognition
- word identification
- word processing
- word recognition
- word segmentation
- word segmentation bakeoff
Other assigned terms:
- ambiguity
- approach
- characters
- chinese word
- corpora
- customization
- dictionaries
- dictionary
- dictionary coverage
- evaluations
- extraction process
- feature
- formalism
- linguistic
- linguistic unit
- methodology
- name entity
- names
- part-of-speech
- probabilities
- process
- segmentation bakeoff
- semantic
- semantic features
- sentence
- simplified chinese
- system description
- technology
- test corpora
- text
- training
- training corpora
- translations
- user
- word
- word lists
- words
