ACL RD-TEC 1.0 Summarization of W04-3236
Paper Title:
CHINESE PART-OF-SPEECH TAGGING: ONE-AT-A-TIME OR ALL-AT-ONCE? WORD-BASED OR CHARACTER-BASED?
CHINESE PART-OF-SPEECH TAGGING: ONE-AT-A-TIME OR ALL-AT-ONCE? WORD-BASED OR CHARACTER-BASED?
Authors: Hwee Tou Ng and Jin Kiat Low
Primarily assigned technology terms:
- algorithm
- analyzer
- beam search
- beam search algorithm
- chinese language processing
- chinese named entity recognition
- chinese parser
- chinese part-of-speech tagging
- chinese word segmentation
- classifier
- cross validation
- cutoff
- dynamic programming
- dynamic programming algorithm
- encoding
- english pos tagger
- entity recognition
- entropy classifier
- feature representation
- hidden markov
- hidden markov model
- java
- language processing
- markov model
- maximum entropy
- maximum entropy classifier
- maximum entropy framework
- modeling
- named entity recognition
- nlp
- parser
- parsing
- part-of-speech tagging
- pos tagger
- pos tagging
- post-processing
- processing
- programming algorithm
- recognition
- search
- search algorithm
- segmentation
- segmentation and pos tagging
- segmenter
- tag assignment
- tagger
- taggers
- tagging
- tagging method
- validation
- word segmentation
- word segmentation and pos tagging
- word segmenter
- word-based approach
Other assigned terms:
- 10-fold cross validation
- ambiguity
- approach
- beam
- character sequence
- characters
- chinese characters
- chinese language
- chinese part-of-speech
- chinese sentence
- chinese treebank
- chinese word
- chinese words
- corpora
- ctb corpus
- document
- english penn treebank
- entropy
- experimental results
- f-measure
- feature
- fmeasure
- heuristic
- implementation
- knowledge
- lexical features
- meaning
- meanings
- measure
- method
- named entity
- nlp tasks
- part-of-speech
- penn chinese treebank
- penn treebank
- penn treebank tag
- penn treebank tag set
- pos tag
- pos tag information
- pos tag sequence
- precision
- probability
- procedure
- punctuation
- segmentation accuracy
- sentence
- sentences
- symbol
- tag information
- tag sequence
- tag set
- tagging accuracy
- tags
- terms
- test corpora
- test data
- text
- training
- training corpus
- training data
- training set
- training text
- training time
- treebank
- treebank tag set
- word
- word boundaries
- word boundary
- word candidate
- word features
- word segmentation accuracy
- word-by-word basis
- words
