ACL RD-TEC 1.0 Summarization of W97-1016
Paper Title:
RESOLVING PP ATTACHMENT AMBIGUITIES WITH MEMORY-BASED LEARNING
RESOLVING PP ATTACHMENT AMBIGUITIES WITH MEMORY-BASED LEARNING
Authors: Jakub Zavrel and Walter Daelemans and Jorn Veenstra
Primarily assigned technology terms:
- algorithm
- ambiguity resolution
- back-off algorithm
- case marking
- categorization
- cd-rom
- classification
- classifier
- classifier algorithm
- clustering
- clustering method
- computational linguistics
- computational natural language learning
- computational system
- computing
- corpus-based approach
- decision tree
- decision trees
- dimension reduction
- disambiguation
- eager learning
- error-driven transformation-based learning
- greedy learning
- induction
- k-nearest neighbor
- k-nearest neighbor classifier
- k-nn
- language analysis
- language learning
- language-processing
- lazy learning
- learning
- learning algorithms
- learning approach
- learning approaches
- linguistic categorization
- loglinear
- machine learning
- machine learning algorithms
- majority voting
- matching
- maximum entropy
- maximum entropy model
- measuring
- memory-based learning
- memory-based pp attachment
- model selection
- modeling
- natural language analysis
- natural language learning
- nearest neighbors
- optimization
- parameter optimization
- phrase attachment disambiguation
- pp attachment disambiguation
- preprocessing
- principal component analysis
- reasoning
- smoothing
- statistical approaches
- statistical disambiguation
- statistical methods
- statistical techniques
- supervised learning
- transformation-based learning
- unsupervised clustering
- unsupervised learning
- validation
- voting
- weighted voting
- weighting
Other assigned terms:
- ambiguity
- analogy
- annotated corpora
- annotated corpus
- annotators
- approach
- association for computational linguistics
- attachment ambiguity
- back-off model
- backoff
- benchmark
- bias
- case
- classification task
- closure principle
- cluster
- co-occurrence
- co-occurrences
- component vector
- conditional probabilities
- context words
- corpora
- data set
- data sparseness
- dimensionality
- distance metric
- distribution
- drosophila
- dutch
- entropy
- events
- exact match
- fact
- feature
- feature set
- feature sets
- frequency distribution
- information gain
- information sources
- information theory
- knowledge
- large corpus
- lexical association
- lexical content
- lexical features
- lexical information
- lexical representation
- lexical similarity
- linguistic
- linguistic knowledge
- linguistics
- logic
- loglinear model
- meaning
- measure
- measures
- method
- methodology
- natural language
- noise
- norm
- parse
- parse tree
- phrase
- phrase attachment
- pp attachment
- pp-attachment
- pragmatic information
- preposition
- prepositional phrase
- prepositional phrase attachment
- probabilities
- process
- query
- random sample
- relation
- relative frequency
- representations
- semantic
- semantic information
- sentence
- sentences
- similarity metric
- similarity metrics
- sources of information
- sparse data
- sparse data problem
- statistics
- structural ambiguity
- symbols
- syntactic categories
- syntactic features
- syntactic information
- syntactic structure
- terms
- test set
- text
- theories
- theory
- training
- training data
- training examples
- training material
- training set
- tree
- treebank
- treebank parse
- trees
- verb
- wall street journal corpus
- wall street journal text
- word
- word features
- wordnet
- words
