ACL RD-TEC 1.0 Summarization of A00-2003
Paper Title:
A PROBABILISTIC GENRE-INDEPENDENT MODEL OF PRONOMINALIZATION
A PROBABILISTIC GENRE-INDEPENDENT MODEL OF PRONOMINALIZATION
Authors: Michael Strube and Maria Wolters
Primarily assigned technology terms:
- algorithm
- anaphora resolution
- annotation tool
- approximation
- bracketing
- classification
- coding
- coreference annotation
- coreference resolution
- corpus annotation
- corpus-based approach
- cross-validation
- data analysis
- decision trees
- discourse interpretation
- generation algorithm
- language generation
- logistic regression
- message understanding
- natural language generation
- nlg system
- np bracketing
- np generation
- phrase coreference resolution
- predictor
- probabilistic pronoun resolution
- pronominalization
- pronoun generation
- pronoun resolution
- pronoun resolution algorithm
- regression
- regression trees
- statistical analysis
- statistical pronominalization
- supervised probabilistic pronoun resolution
- unsupervised algorithm
Other assigned terms:
- 10-fold cross-validation
- adjunct
- ambiguity
- anaphora
- animacy
- annotation
- annotation scheme
- annotators
- approach
- binomial distribution
- brown corpus
- case
- centering model
- chunk
- class information
- coding scheme
- cognitive
- cognitive science
- concept
- coreference chains
- corpora
- data set
- determiners
- discourse
- discourse entities
- discourse entity
- discourse information
- discourse structure
- distribution
- fact
- feature
- feature-value pair
- generation
- genre
- genre-specific corpora
- grammatical role
- head noun
- heuristics
- interpretation
- labeling
- large corpora
- linear combination
- linguistics
- linguists
- logistic regression model
- message
- methodology
- morphemes
- morpho-syntactic information
- natural language
- noun phrase
- noun phrase coreference
- nouns
- paragraphs
- parallelism
- parse
- part-of-speech
- penn treebank
- personal pronouns
- phrase
- phrase coreference
- prediction accuracy
- predictive power
- probabilistic model
- probability
- procedure
- pronoun
- pronouns
- proper name
- regression model
- research topic
- segments
- selectional restrictions
- semantic
- semantic categories
- sentences
- sparse data
- statistical models
- stem
- structural annotation
- stylistic variation
- subject position
- subordinate clauses
- synsets
- syntactic constraints
- syntactic function
- syntactic information
- terms
- test data
- text
- thematic role
- training
- training and test data
- training data
- training data set
- treebank
- trees
- understanding
- user
- utterance
- word-net
- wordnet
- wordnet synsets
- words
