ACL RD-TEC 1.0 Summarization of A97-1018
Paper Title:
CSEG&TAGL.0: A PRACTICAL WORD SEGMENTER AND POS TAGGER FOR CHINESE TEXTS
CSEG&TAGL.0: A PRACTICAL WORD SEGMENTER AND POS TAGGER FOR CHINESE TEXTS
Authors: Sun Maosong and Shen Dayang and Huang Changning
Primarily assigned technology terms:
- algorithm
- c + +
- categorization
- chinese information processing
- chinese word segmentation
- classifier
- computing
- dynamic programming
- dynamic programming algorithm
- information processing
- information retrieval
- part-of-speech tagging
- pos tagger
- pos tagging
- pre-processing
- processing
- programming algorithm
- programming language
- recognition
- searching
- segmentation
- segmentation and pos tagging
- segmenter
- speech recognition
- tagger
- tagging
- text categorization
- text-to-speech
- text-to-speech conversion
- tile
- word segmentation
- word segmentation and pos tagging
- word segmenter
Other assigned terms:
- adjective
- adverb
- ambiguity
- approach
- bigram
- bigram model
- cache
- case
- characters
- chinese language
- chinese word
- community
- concept
- corpora
- dictionary
- experimental results
- fact
- heuristic
- heuristic rules
- input text
- knowledge
- knowledge base
- large corpora
- lexicon
- mechanisms
- method
- mutual information
- names
- part-of-speech
- parts of speech
- personal names
- pos bigram
- precision
- probability
- process
- pronunciation
- proper noun
- sentence
- sentences
- statistical data
- statistical information
- statistics
- structural information
- syntactic rules
- system architecture
- tag sequence
- tagged corpus
- tagging precision
- technology
- terms
- text
- textual corpora
- training
- unigram
- word
- word formation
- word formation rules
- word frequencies
- word frequency
- word sequence
- word sequences
- word string
- words
