ACL RD-TEC 1.0 Summarization of N06-1023
Paper Title:
A FULLY-LEXICALIZED PROBABILISTIC MODEL FOR JAPANESE SYNTACTIC AND CASE STRUCTURE ANALYSIS
A FULLY-LEXICALIZED PROBABILISTIC MODEL FOR JAPANESE SYNTACTIC AND CASE STRUCTURE ANALYSIS
Authors: Daisuke Kawahara and Sadao Kurohashi
Primarily assigned technology terms:
- algorithm
- analysis method
- analyzer
- approximation
- case analysis
- case assignment
- case frame construction
- case structure analysis
- chunking-based dependency analysis
- dependency analysis
- discourse analysis
- ellipsis resolution
- em algorithm
- frame construction
- language understanding
- learning
- learning technique
- machine learning
- maximum likelihood
- morphological analyzer
- natural language understanding
- optimization
- parser
- parsers
- parsing
- pglr-based syntactic analysis
- probability estimation
- semantic role labeling
- semantic structure analysis
- splitting
- statistical method
- statistical parsers
- structure analysis
- syntactic analysis
- syntactic parser
- topic marker
- weighting
Other assigned terms:
- ambiguity
- anaphora
- annotation
- bunsetsu
- case
- case frame
- case structure
- dependency formalism
- dependency structures
- discourse
- edr corpus
- ellipsis
- embedded clause
- error rate
- estimation
- experimental results
- formalism
- frame
- framenet
- generation
- generative model
- generative probability
- gold standard
- hand-tagged corpus
- index
- inflection
- interpretation
- labeling
- large corpus
- lexical information
- lexical preference
- likelihood
- logical form
- meaning
- meanings
- method
- natural language
- natural language text
- newspaper corpus
- parse
- part-of-speech
- penn treebank
- phrase
- predicate-argument
- predicate-argument structure
- probabilistic model
- probabilities
- probability
- process
- propbank
- punctuation
- punctuation mark
- punctuation marks
- relation
- role labeling
- selectional preference
- semantic
- semantic role
- semantic structure
- sense ambiguity
- sentence
- sentences
- slot
- sparse data
- sparse data problem
- statistics
- subordinate clause
- syntactic ambiguity
- syntactic relation
- syntactic relations
- syntactic structure
- syntactic structures
- system performance
- tags
- technique
- technology
- test set
- text
- text corpus
- thesaurus
- tree
- treebank
- understanding
- verb
- verb sense
- verb senses
- web corpus
- word
- word order
- words
