ACL RD-TEC 1.0 Summarization of W06-2935
Paper Title:
LANGUAGE INDEPENDENT PROBABILISTIC CONTEXT-FREE PARSING BOLSTERED BY MACHINE LEARNING
LANGUAGE INDEPENDENT PROBABILISTIC CONTEXT-FREE PARSING BOLSTERED BY MACHINE LEARNING
Authors: Michael Schiehlen and Kristina Spranger
Primarily assigned technology terms:
- algorithm
- back-off smoothing
- classification
- computational linguistics
- computational natural language learning
- context-free parser
- context-free parsing
- cross validation
- dependency parsing
- knowledge bases
- language learning
- learner
- learning
- learning approach
- learning system
- listing
- machine learner
- machine learning
- maxent
- multilingual dependency parsing
- natural language learning
- parser
- parsing
- probabilistic context-free parsing
- probabilistic parser
- smoothing
- statistical parser
- statistical parsing
- statistical system
- subcategorization
- tagger
- validation
- viterbi
- viterbi algorithm
Other assigned terms:
- 10-fold cross validation
- adjunct
- annotation
- annotators
- approach
- association for computational linguistics
- bigram
- bigram model
- case
- classification problem
- conjunct
- conll-x
- context free rule
- context-free grammars
- dependency grammars
- dependency relation
- dependency relations
- dependency structure
- dependency trees
- development set
- evaluations
- f-score
- fact
- feature
- feature information
- frame
- grammar
- grammar rules
- grammars
- knowledge
- language-dependent knowledge
- lemma
- lexical category
- lexical items
- lexical rules
- linguistics
- method
- morphological information
- natural language
- negra
- parse
- parse tree
- parsing problem
- pcfg
- penn treebank
- phrase
- pos tag
- pos tag information
- predicate-argument
- predicate-argument structure
- probabilities
- probability
- process
- projection
- punctuation
- relation
- root node
- sentences
- slot
- subcategorization frame
- subcategorization frames
- suffixes
- symbols
- syntactic context
- tag information
- tags
- terms
- test data
- test set
- tokens
- toolkit
- training
- training data
- training set
- tree
- treebank
- trees
- unbounded dependencies
- unigram
- word
- words
