ACL RD-TEC 1.0 Summarization of J97-4004
Paper Title:
CRITICAL TOKENIZATION AND ITS PROPERTIES
CRITICAL TOKENIZATION AND ITS PROPERTIES
Primarily assigned technology terms:
- algorithm
- ambiguity resolution
- automatic segmentation
- boosting
- boundary disambiguation
- character string generation
- computational linguistics
- disambiguation
- finite-state transducer
- graph representation
- identification
- inferencing
- language processing
- language processing systems
- listing
- matching
- maximal matching
- maximum matching
- natural language processing
- parsing
- path evaluation
- path finding
- processing
- reasoning
- searching
- segmentation
- sentence generation
- sentence parsing
- sentence tokenization
- sentence understanding
- shortest path
- splitting
- string matching
- summarization
- tokenization
- tokenization disambiguation
- tokenization implementation
- transducer
- weighted finite-state transducer
Other assigned terms:
- alphabet
- ambiguity
- annotation
- approach
- automatic segmentation model
- case
- categorical ambiguity
- characters
- chinese characters
- chinese corpus
- combinational ambiguity
- compact representation
- computational complexity
- concept
- concepts
- derivation
- dictionary
- discourse
- disjunctive ambiguity
- english dictionary
- evaluation function
- fact
- formalization
- generation
- generation process
- grammar
- grammars
- heuristic
- heuristics
- implementation
- index
- inferences
- interpretation
- knowledge
- language syntax
- lemma
- linear time
- linguistic
- linguistic theories
- linguistics
- mapping
- maps
- mathematical model
- mathematics
- meaning
- meanings
- morphemes
- natural language
- natural language syntax
- natural languages
- opinion
- opinions
- parse
- parse tree
- procedure
- process
- production rules
- relation
- research and development
- russian
- semantic
- sentence
- sentences
- statistics
- substring
- syntactic graph
- syntax
- syntax and semantics
- term
- terms
- text
- textbook
- theorem
- theories
- theory
- tokens
- tree
- trees
- understanding
- unigram
- word
- word boundary
- word string
- word strings
- words