ACL RD-TEC 1.0 Summarization of W06-0117
Paper Title:
FRANCE TELECOM R&D BEIJING WORD SEGMENTER FOR SIGHAN BAKEOFF 2006
FRANCE TELECOM R&D BEIJING WORD SEGMENTER FOR SIGHAN BAKEOFF 2006
Authors: Wu Liu and Heng Li and Yuan Dong and Nan He and Haitao Luo and Haila Wang
Primarily assigned technology terms:
- abbreviations recognition
- algorithm
- anaphora resolution
- chinese language processing
- chinese word segmentation
- computational linguistics
- entity identification
- entity recognition
- entity recognizer
- entity recognizers
- identification
- language processing
- learning
- maximum entropy
- maximum entropy approach
- named entity identification
- named entity recognition
- named entity recognizer
- ne recognizer
- processing
- recognition
- recognizer
- search
- segmentation
- tagging
- tbl training
- tokenization
- transformation-based learning
- viterbi
- viterbi search
- word recognition
- word segmentation
- word segmentation bakeoff
- word segmentation task
Other assigned terms:
- abbreviations
- anaphora
- approach
- association for computational linguistics
- chinese language
- chinese text
- chinese word
- chinese words
- contextual information
- contextual word
- dictionary
- entropy
- f-score
- knowledge
- language model
- lexicon
- linguistics
- method
- named entities
- named entity
- names
- ngram
- ngram language model
- organization names
- person names
- precision
- rule template
- segmentation bakeoff
- statistical framework
- statistical model
- system description
- tag information
- tags
- test corpus
- text
- theory
- toolkit
- training
- training corpus
- training data
- trigram
- trigram language model
- window size
- word
- word information
- word lists
- word segmentation performance
- word-based language model
- words
