ACL RD-TEC 1.0 Summarization of P05-1038
Paper Title:
LEXICALIZATION IN CROSSLINGUISTIC PROBABILISTIC PARSING: THE CASE OF FRENCH
LEXICALIZATION IN CROSSLINGUISTIC PROBABILISTIC PARSING: THE CASE OF FRENCH
Authors: Abhishek Arun and Frank Keller
Primarily assigned technology terms:
- algorithm
- argument identification
- beam search
- bikel parser
- binary branching
- bracketing
- capitalization
- chunker
- chunking
- cky algorithm
- collapsing
- computing
- crosslinguistic parsing
- decoding
- full parsing
- hyphenation
- identification
- learner
- lexicalization
- likelihood estimation
- maximum likelihood
- maximum likelihood estimation
- memory-based learner
- parser
- parsing
- parsing engine
- pos tagging
- probabilistic parsing
- probabilistic parsing engine
- probability function
- scoring
- search
- subcategorization
- tagging
- tree transformation
- treebank parsing
Other assigned terms:
- adverb
- analogy
- annotation
- annotation scheme
- annotation schemes
- approach
- baseline model
- beam
- bigram
- bigram model
- case
- chunks
- compound preposition
- compounds
- context-free grammars
- context-free rule
- crosslinguistic parsing research
- data set
- data sets
- data sparseness
- dependency treebank
- dependency trees
- derivation
- determiners
- development set
- distance measure
- distribution
- empty categories
- estimation
- f-score
- feature
- feature vectors
- finite verb
- french
- frequency distribution
- generation
- geometric mean
- gold standard
- grammar
- grammar rules
- grammars
- head-word
- heuristic
- heuristics
- implementation
- infinitival clause
- inflection
- lexical items
- lexicalized model
- lexicon
- likelihood
- mapping
- measure
- measures
- method
- morphological information
- negation
- negra
- noun phrases
- nucleus
- parse
- parse tree
- parsing accuracy
- parsing models
- parsing research
- part of speech
- part of speech tags
- pcfg
- penn treebank
- phrase
- pos tag
- prague dependency treebank
- precision
- preposition
- prepositions
- probabilistic context-free grammars
- probabilities
- probability
- process
- pronouns
- ptb
- punctuation
- punctuation marks
- relative clause
- sentence
- sentences
- sister-head model
- sparse data
- statistical significance
- subcategorization frames
- subordinate clauses
- suffix
- symbol
- syntactic categories
- syntactic category
- syntactic structure
- syntactic structures
- syntactic tag
- tag information
- tagging accuracy
- tagging model
- tags
- tagset
- test data
- test set
- training
- training phase
- training set
- transformation
- tree
- treebank
- treebank annotation
- trees
- unlabeled dependency
- verb
- verb phrase
- word
- word order
- words
