ACL RD-TEC 1.0 Summarization of J05-4002
Paper Title:
CO-OCCURRENCE RETRIEVAL: A FLEXIBLE FRAMEWORK FOR LEXICAL DISTRIBUTIONAL SIMILARITY
CO-OCCURRENCE RETRIEVAL: A FLEXIBLE FRAMEWORK FOR LEXICAL DISTRIBUTIONAL SIMILARITY
Primarily assigned technology terms:
- ambiguity resolution
- approximation
- automatic thesaurus extraction
- automatic thesaurus generation
- co-occurrence retrieval
- collocation analysis
- computational linguistics
- computing
- cross validation
- disambiguation
- document retrieval
- five-fold cross validation
- information retrieval
- language generation
- language modeling
- language processing
- modeling
- natural language generation
- natural language processing
- nearest neighbors
- nlp
- optimization
- parameter optimization
- parameter setting
- parse selection
- parser
- pp-attachment ambiguity resolution
- predictor
- probabilistic parse selection
- processing
- pseudo-disambiguation
- recognition
- retrieval process
- sense disambiguation
- sense disambiguation task
- set comparison
- set comparison technique
- similarity calculation
- similarity-based smoothing
- smoothing
- speech recognition
- statistical nlp
- statistical parser
- statistical technique
- statistical test
- text simplification
- thesaurus extraction
- thesaurus generation
- thesaurus generation and pseudo-disambiguation
- thesaurus generation task
- unsupervised approach
- validation
- word sense disambiguation
Other assigned terms:
- ambiguity
- analogy
- approach
- arithmetic mean
- association for computational linguistics
- asymmetric relationship
- attachment ambiguity
- british national corpus
- case
- cluster
- co-occurrence
- co-occurrences
- coefficient
- collocation
- computer program
- concept
- concepts
- correlation
- data set
- development set
- dice
- dice coefficient
- disambiguation task
- distribution
- distributional similarity
- document
- domain knowledge
- english text
- entropy
- error rate
- events
- f-score
- fact
- feature
- feature sets
- generation
- generation task
- gold standard
- grammatical relation
- grammatical relations
- hyponymy
- hypothesis
- implementation
- information-theoretic similarity theorem
- interpretation
- knowledge
- kullback-leibler divergence
- language change
- language model
- language models
- lexical items
- lexical knowledge
- lexical similarity
- linguistic
- linguistics
- local context
- log-likelihood
- log-likelihood ratio
- meaning
- measure
- measures
- model context
- mutual information
- natural language
- norm
- noun hierarchy
- nouns
- pairs of words
- parameter settings
- parse
- part of speech
- parts of speech
- phrase
- phrase attachment
- pointwise mutual information
- pp-attachment
- pp-attachment ambiguity
- precision
- prediction task
- preposition
- prepositional phrase
- prepositional phrase attachment
- probabilities
- probability
- probability distributions
- probability estimates
- process
- pseudo-disambiguation task
- query
- recognition task
- relation
- retrieval model
- semantic
- semantic classes
- semantic measure
- semantic similarity
- sentences
- similarity between words
- similarity function
- similarity measure
- similarity measures
- similarity scores
- similarity threshold
- sparse data
- sparse data problem
- speech recognition task
- standard deviation
- statistical model
- substitutability
- synonymy
- target word
- technique
- term
- terms
- test data
- test data set
- test set
- text
- theorem
- thesaurus
- tokens
- training
- training corpus
- training data
- transformation
- unigram
- user
- utterance
- vector space
- verb
- word
- word frequency
- word sense
- word senses
- word similarity
- wordnet
- words
