ACL RD-TEC 1.0 Summarization of W06-0121
Paper Title:
CHINESE WORD SEGMENTATION WITH MAXIMUM ENTROPY AND N-GRAM LANGUAGE MODEL
CHINESE WORD SEGMENTATION WITH MAXIMUM ENTROPY AND N-GRAM LANGUAGE MODEL
Authors: Xinhao Wang and Xiaojun Lin and Dianhai Yu and Hao Tian and Xihong Wu
Primarily assigned technology terms:
- algorithm
- chinese language processing
- chinese word segmentation
- classification
- computational linguistics
- dynamic programming
- dynamic programming algorithm
- language processing
- learning
- learning process
- machine perception
- matching
- maximum entropy
- maximum entropy model
- natural language processing
- processing
- programming algorithm
- scoring
- segmentation
- word processing
- word segmentation
- word segmentation bakeoff
- word segmentation task
Other assigned terms:
- ambiguity
- approach
- association for computational linguistics
- backoff
- bigram
- bigram language model
- bigram model
- characters
- chinese language
- chinese word
- classification task
- corpora
- dictionaries
- dictionary
- entropy
- language model
- lexical tree
- linguistics
- method
- n-gram
- n-gram language model
- names
- natural language
- organization names
- process
- processing strategy
- punctuation
- relation
- segmentation bakeoff
- sentence
- substring
- subtree
- suffix
- suffixes
- system description
- test data
- test set
- toolkit
- training
- training data
- training set
- tree
- unigram
- vocabulary
- word
- word boundaries
- words
