ACL RD-TEC 1.0 Summarization of W99-0608
Paper Title:
IMPROVING POS TAGGING USING MACHINE-LEARNING TECHNIQUES
IMPROVING POS TAGGING USING MACHINE-LEARNING TECHNIQUES
Authors: Lluis Marquez and Horacio Rodriguez and Josep Carmona and Josep Montolio
Primarily assigned technology terms:
- algorithm
- backoff approach
- bagging
- boosting
- bootstrap
- bootstrapping
- bootstrapping algorithm
- categorization
- classification
- classifier
- classifiers
- combined classifier
- context-sensitive spelling
- context-sensitive spelling correction
- cross-validation
- decision tree
- decision trees
- disambiguation
- disambiguation algorithm
- dynamic programming
- english pos tagger
- error reduction
- feature selection
- genetic algorithms
- induction
- induction algorithm
- iterative process
- learning
- learning algorithm
- learning algorithms
- learning techniques
- linear interpolation
- machine learning
- machine learning techniques
- machine-learning
- modelling
- neural networks
- nlp
- optimization
- parser
- pos tagger
- pos tagging
- resampling
- rule-induction
- shallow parser
- speech tagger
- spelling
- spelling correction
- statistical tagger
- supervised learning
- tagger
- taggers
- tagging
- text categorization
- tree induction
- tree induction algorithm
- tree-based learning
- tuning
- viterbi
- viterbi algorithm
- voting
Other assigned terms:
- 10-fold cross-validation
- acronym
- adjective
- adverb
- ambiguity
- ambiguous word
- ambiguous words
- annotated corpora
- approach
- backoff
- case
- characters
- chi-square statistic
- classification problem
- classification tasks
- collocational information
- compact representation
- composition
- constraint grammars
- contextual information
- contextual model
- corpora
- cross-validation experiment
- data set
- data sparseness
- dictionary
- distribution
- error rate
- experimental results
- fact
- feature
- generation
- grammars
- human knowledge
- implementation
- independence assumption
- index
- information gain
- interpolation
- knowledge
- language model
- lexical information
- lexicon
- local context
- method
- morphological features
- morphological information
- n-gram
- orthography
- part of speech
- part-of-speech
- part-of-speech tags
- penn treebank
- penn treebank tag
- penn treebank tag set
- penn treebank tagset
- pos tag
- precision
- prediction accuracy
- probabilities
- probability
- probability distribution
- procedure
- process
- proper noun
- runtime
- sentence
- sentence level
- statistic
- style
- suffix
- suffixes
- symbols
- tag set
- tagging accuracy
- tags
- tagset
- target word
- technique
- terms
- test set
- text
- training
- training corpus
- training data
- training examples
- training material
- training set
- tree
- treebank
- treebank tag set
- trees
- user
- verb
- vocabulary
- word
- word form
- words
- wsj corpus
