ACL RD-TEC 1.0 Summarization of P02-1034
Paper Title:
NEW RANKING ALGORITHMS FOR PARSING AND TAGGING: KERNELS OVER DISCRETE STRUCTURES, AND THE VOTED PERCEPTRON
NEW RANKING ALGORITHMS FOR PARSING AND TAGGING: KERNELS OVER DISCRETE STRUCTURES, AND THE VOTED PERCEPTRON
Authors: Michael Collins and Nigel Duffy
Primarily assigned technology terms:
- algorithm
- approximation
- atis
- beam search
- boosting
- capitalization
- classification
- computational linguistics
- dynamic programming
- dynamic programming algorithm
- encoding
- error reduction
- exact parsing
- image classification
- inner product
- kernel
- kernels
- language processing
- learning
- learning algorithms
- learning methods
- learning task
- left-to-right search
- machine learning
- markov random field
- maximum entropy
- maximum-entropy
- named-entity extraction
- named-entity recognition
- natural language processing
- nlp
- parameter estimation
- parsing
- part-of-speech tagging
- perceptron
- perceptron algorithm
- processing
- programming algorithm
- question-answering
- question-answering system
- ranking
- recognition
- reranking
- search
- support vector machines
- tagger
- taggers
- tagging
- training algorithm
- tree algorithm
- tree kernel
- tuning
- voted perceptron
- voted perceptron algorithm
- voting
- weighting
Other assigned terms:
- approach
- baseline model
- beam
- case
- chunk
- chunks
- computational complexity
- context-free grammar
- context-free grammars
- data set
- data sets
- derivations
- development set
- dimensionality
- entropy
- error rate
- estimation
- experimental results
- f-measure
- feature
- feature set
- feature space
- feature vector
- feature vectors
- finite set
- grammar
- grammars
- hypotheses
- linguistics
- measure
- method
- named-entity
- natural language
- parameter values
- parse
- parse tree
- part-of-speech
- part-of-speech tags
- pcfg
- polynomial time
- precision
- probabilistic model
- probabilities
- probability
- probability model
- procedure
- recursion
- relative error reduction
- representations
- running time
- runtime
- sentence
- sentences
- set size
- similarity measure
- sparse data
- statistics
- stochastic context-free grammars
- style
- sub-tree
- subgraph
- subtree
- subtrees
- support vector
- svms
- symbols
- tag sequence
- tagging model
- tagging task
- tags
- terms
- test data
- test set
- text
- theory
- training
- training and test data
- training data
- training examples
- training phase
- training set
- training set size
- training time
- tree
- treebank
- trees
- wall street journal text
- web pages
- word
- word features
- words
