ACL RD-TEC 1.0 Summarization of W00-1207
Paper Title:
STATISTICALLY-ENHANCED NEW WORD IDENTIFICATION IN A RULE-BASED CHINESE SYSTEM
STATISTICALLY-ENHANCED NEW WORD IDENTIFICATION IN A RULE-BASED CHINESE SYSTEM
Authors: Andi Wu and Zixin Jiang
Primarily assigned technology terms:
- chinese parser
- computing
- dictionary lookup
- disambiguation
- full parsing
- identification
- language processing
- language processing system
- language understanding
- lexical acquisition
- matching
- morphology
- name identification
- natural language processing
- natural language processing system
- natural language understanding
- parser
- parsing
- processing
- robust parsing
- rule-based system
- segmentation
- segmentation process
- sentence analysis
- statistical approaches
- statistical methods
- syntactic parser
- word guessing
- word identification
- word identification mechanism
- word segmentation
Other assigned terms:
- adjective
- ambiguity
- approach
- case
- character sequence
- characters
- chinese characters
- chinese language
- chinese text
- corpora
- derivational morphology
- dictionary
- fact
- heuristic
- heuristic rules
- hypotheses
- hypothesis
- implementation
- joint probability
- lattice
- likelihood
- measure
- mechanisms
- method
- names
- natural language
- noise
- nouns
- parse
- parse tree
- parsed corpus
- parsing process
- parts of speech
- pos sequence
- precision
- probabilities
- probability
- procedure
- process
- proper name
- proper names
- sentence
- sentences
- sparse data
- sparse data problem
- statistics
- syllables
- syntactic category
- syntactic structures
- text
- text corpora
- text corpus
- training
- training corpus
- tree
- trees
- understanding
- verb
- word
- word boundary
- word candidate
- word formation
- word lattice
- word lists
- word string
- words
- written texts
