ACL RD-TEC 1.0 Summarization of P06-1043
Paper Title:
RERANKING AND SELF-TRAINING FOR PARSER ADAPTATION
RERANKING AND SELF-TRAINING FOR PARSER ADAPTATION
Authors: David McClosky and Eugene Charniak and Mark Johnson
Primarily assigned technology terms:
- bracketing
- broad-coverage parser
- charniak parser
- computational linguistics
- cross-validation
- disfluency modeling
- error reduction
- logistic regression
- model selection
- modeling
- parse selection
- parser
- parser adaptation
- parser improvement
- parser-reranker
- parsers
- parsing
- part of speech tagging
- randomization
- randomization test
- regression
- reranking
- self-training
- speech tagging
- statistical analysis
- statistical parsers
- statistical parsing
- tagging
- tuning
- voting
- weighting
- wsj-trained reranker
Other assigned terms:
- american news corpus
- approach
- association for computational linguistics
- biology
- biomedical literature
- brown corpus
- case
- corpora
- data set
- data sparsity
- discriminative model
- distribution
- evaluations
- f-measure
- f-score
- fact
- feature
- feature weights
- grammar
- hypothesis
- linear model
- linguistics
- logistic regression model
- measure
- medical corpora
- n-best list
- news corpus
- null hypothesis
- oracle
- parse
- parser portability
- parsing accuracy
- parsing model
- parsing models
- part of speech
- penn treebank
- penn wsj test set
- portability
- precision
- prepositions
- procedure
- regression model
- sentence
- sentence boundaries
- sentence level
- sentences
- statistics
- subcorpus
- switchboard corpus
- syntactic information
- technique
- terms
- test corpora
- test set
- text
- textbook
- training
- training corpora
- training corpus
- training data
- training set
- treebank
- treebank corpus
- trees
- vocabulary
- words
- wsj treebank
