ACL RD-TEC 1.0 Summarization of I05-3027
Paper Title:
A CONDITIONAL RANDOM FIELD WORD SEGMENTER FOR SIGHAN BAKEOFF 2005
A CONDITIONAL RANDOM FIELD WORD SEGMENTER FOR SIGHAN BAKEOFF 2005
Authors: Huihsin Tseng and Pichuan Chang and Galen Andrew and Daniel Jurafsky and Christopher Manning
Primarily assigned technology terms:
Other assigned terms:
- affix
- affixes
- case
- characters
- chinese treebank
- corpora
- external knowledge
- f-score
- fact
- feature
- knowledge
- lambda
- linguistic
- linguistic features
- measure
- morphological features
- morphological information
- n-gram
- n-grams
- nouns
- punctuation
- sentence
- sequence model
- suffix
- suffixes
- syntactic knowledge
- technique
- term
- testing data
- training
- training corpus
- training data
- training set
- treebank
- understanding
- unigram
- unknown word model
- word
- word features
- word model
- words