ACL RD-TEC 1.0 Summarization of W03-1025
Paper Title:
A MAXIMUM ENTROPY CHINESE CHARACTER-BASED PARSER
A MAXIMUM ENTROPY CHINESE CHARACTER-BASED PARSER
Primarily assigned technology terms:
Other assigned terms:
- ambiguity
- approach
- baseline model
- boundary information
- characters
- chinese text
- chinese treebank
- chinese word
- contextfree grammar
- distribution
- entropy
- f-measure
- fact
- grammar
- heuristic
- knowledge
- language model
- lexical features
- lexical level
- lexicon
- mapping
- measure
- measures
- method
- mutual information
- parse
- parse tree
- parser output
- parsing accuracy
- part-ofspeech
- pcfg
- pos information
- pos tag
- probability
- probability distribution
- procedure
- representations
- segmentation accuracy
- sentence
- sentences
- statistical approach
- syntactic information
- syntactic structure
- tags
- test set
- text
- tokens
- training
- training corpus
- training data
- training set
- training size
- tree
- treebank
- trees
- unigram
- unigram probability
- word
- word boundaries
- word boundary
- word level
- words
