ACL RD-TEC 1.0 Summarization of W06-3604
Paper Title:
ALL-WORD PREDICTION AS THE ULTIMATE CONFUSIBLE DISAMBIGUATION
ALL-WORD PREDICTION AS THE ULTIMATE CONFUSIBLE DISAMBIGUATION
Primarily assigned technology terms:
- algorithm
- approximation
- automatic speech recognition
- back-off smoothing
- classification
- classifier
- classifiers
- computational linguistics
- computing
- data preparation
- database
- decision tree
- decision trees
- decision-tree
- decision-tree induction
- decision-tree induction algorithm
- disambiguation
- igtree algorithm
- igtree decision-tree induction
- illustration
- induction
- induction algorithm
- information retrieval
- iterative procedure
- k-nearest neighbor
- k-nn
- language engineering
- language modeling
- language processing
- learner
- learning
- learning algorithm
- learning algorithms
- learning method
- machine learning
- machine learning algorithms
- matching
- memory-based learning
- modeling
- multi-label classification
- natural language processing
- neighbor classification
- one-shot learning
- parser
- prediction system
- predictor
- processing
- processor
- recognition
- recognition systems
- searching
- smoothing
- speech recognition
- speech recognition systems
- tokenizer
- trie construction
- word prediction
- word processor
Other assigned terms:
- american english
- approach
- association for computational linguistics
- bigram
- bigram model
- brown corpus
- case
- classification tasks
- content words
- context window
- contextual information
- convergence
- corpora
- data consortium
- data set
- data sets
- disambiguation task
- document
- document collections
- english language
- experimental results
- experimental setting
- fact
- feature
- feature space
- feature value
- function word
- function words
- generation
- genre
- heuristic
- information gain
- information science
- interpretation
- knowledge
- labeling
- language model
- large feature space
- leaf
- linguistic
- linguistic data
- linguistic data consortium
- linguistics
- method
- methodology
- n-gram
- n-gram models
- natural language
- penn treebank
- phrase
- phrase structure
- prediction accuracy
- prediction model
- prediction task
- procedure
- process
- punctuation
- relation
- reuters corpus
- root node
- sentence
- set size
- statistics
- symbols
- syntactic phrase
- syntactic phrase structure
- syntactic structure
- terms
- test set
- text
- textual corpora
- tokens
- training
- training data
- training examples
- training material
- training set
- training set size
- tree
- treebank
- trees
- unigram
- word
- word features
- words
- world knowledge
