ACL RD-TEC 1.0 Summarization of P06-1129
Paper Title:
EXPLORING DISTRIBUTIONAL SIMILARITY BASED MODELS FOR QUERY SPELLING CORRECTION
EXPLORING DISTRIBUTIONAL SIMILARITY BASED MODELS FOR QUERY SPELLING CORRECTION
Authors: Mu Li and Muhua Zhu and Yang Zhang and Ming Zhou
Primarily assigned technology terms:
- algorithm
- candidate ranking
- classification
- clustering
- computational linguistics
- damerau-levenshtein distance
- distributional similarity estimation
- error model estimation
- expectation maximization
- generalized iterative scaling
- illustration
- iterative scaling
- knowledge acquisition
- language model smoothing
- learning
- levenshtein
- machine translation
- machine translation training
- maximum entropy
- maximum entropy model
- model estimation
- model smoothing
- model training
- model training and testing
- modeling
- normalization
- part-ofspeech tagging
- personal computer
- processing
- query spelling
- ranking
- search
- search engine
- search engines
- semantic knowledge acquisition
- similarity estimation
- smoothing
- spell checker
- spelling
- spelling correction
- statistical machine translation
- statistical sequence inference
- tagging
- training algorithm
- translation training
- unsupervised approach
- viterbi
- viterbi algorithm
- web search
- word bigram
- word clustering
Other assigned terms:
- annotation
- annotators
- approach
- association for computational linguistics
- bayesian framework
- bigram
- bigram model
- binary features
- checker
- cognitive
- confusion probability
- context words
- cosine distance
- data set
- distribution
- distributional similarity
- edit distance
- entropy
- entropy models
- error rate
- estimation
- euclidean distance
- evaluation measures
- experimental results
- fact
- feature
- feature sets
- feature value
- feature weights
- generation
- generative models
- heuristic
- interpolation
- knowledge
- language model
- language model probability
- levenshtein edit distance
- lexicon
- linear combination
- linguistics
- maximum entropy models
- measure
- measures
- method
- model parameter
- model probability
- n-best list
- n-gram
- natural language
- part-ofspeech
- phonetic similarity
- posterior
- posterior probability
- probabilistic model
- probabilistic models
- probabilities
- probability
- process
- processing tasks
- pronunciation
- queries
- query
- query term
- search query
- search space
- semantic
- semantic knowledge
- similarity between words
- similarity measure
- similarity measures
- source channel model
- spelling error
- statistical language model
- statistical models
- statistical sequence
- statistics
- synonyms
- term
- term frequency
- terms
- test set
- training
- training data
- training samples
- training set
- training size
- user
- vector space
- vocabulary
- web query
- weighted edit distance
- word
- word bigram model
- words
