ACL RD-TEC 1.0 Summarization of W06-0115
Paper Title:
THE THIRD INTERNATIONAL CHINESE LANGUAGE PROCESSING BAKEOFF: WORD SEGMENTATION AND NAMED ENTITY RECOGNITION
THE THIRD INTERNATIONAL CHINESE LANGUAGE PROCESSING BAKEOFF: WORD SEGMENTATION AND NAMED ENTITY RECOGNITION
Primarily assigned technology terms:
- character encoding
- chinese language processing
- chinese named entity recognition
- computational linguistics
- computing
- encoding
- entity recognition
- identification
- information processing
- information retrieval
- language processing
- local encoding
- machine translation
- named entity recognition
- natural language processing
- ner annotation
- parsing
- part of speech tagging
- pre-processing
- processing
- question answering
- recognition
- reference resolution
- scoring
- scoring script
- segmentation
- speech tagging
- splitting
- taggers
- tagging
- tokenization
- word handling
- word identification
- word segmentation
Other assigned terms:
- annotation
- approach
- association for computational linguistics
- automatic conversion
- baseline performance
- binomial distribution
- broadcast news
- case
- characters
- chinese language
- chinese treebank
- comparable corpora
- corpora
- data consortium
- distribution
- entity type
- evaluations
- f-measure
- f-score
- fact
- knowledge
- language processing tasks
- lexica
- lexical resources
- linguistic
- linguistic data
- linguistic data consortium
- linguistics
- manual intervention
- measures
- named entities
- named entity
- names
- natural language
- natural language processing tasks
- organization names
- out-of-vocabulary word
- part of speech
- part-of-speech
- phrase
- precision
- probability
- procedure
- processing tasks
- sentence
- speech information
- tags
- technologies
- terms
- test corpora
- test data
- text
- theorem
- training
- training corpus
- training data
- treebank
- vocabulary
- web page
- word
- words
- xml format
