ACL RD-TEC 1.0 Summarization of W05-1202
Paper Title:
THE DISTRIBUTIONAL SIMILARITY OF SUB-PARSES
THE DISTRIBUTIONAL SIMILARITY OF SUB-PARSES
Authors: Julie Weeds and David Weir and Bill Keller
Primarily assigned technology terms:
- approximation
- automatic thesaurus construction
- computing
- corpus construction
- entailment recognition
- extractor
- feature extraction
- identification
- matching
- maximum likelihood
- mining
- mobile phone
- paraphrasing
- parser
- rasp parser
- recognition
- recognizing textual entailment
- shallow parser
- similarity calculation
- template matching
- textual entailment recognition
- thesaurus construction
- weighting
Other assigned terms:
- anchor
- anchors
- approach
- british national corpus
- case
- co-occurrence
- co-occurrences
- concept
- corpora
- data sparseness
- dependency relations
- distributional similarity
- entailment
- feature
- feature type
- feature types
- frequency counts
- generalisation
- gold standard
- grammatical relation
- grammatical relations
- hypotheses
- hypothesis
- kl divergence
- lexical coverage
- lexical resources
- lexical semantic
- lexical similarity
- lexical variation
- likelihood
- meaning
- meanings
- measure
- measures
- method
- mutual information
- ontology
- pairs of words
- paraphrase
- paraphrase corpus
- paraphrases
- parse
- parse tree
- parsed corpus
- parts of speech
- phrase
- probabilities
- process
- relation
- semantic
- semantic similarity
- sentence
- sentences
- similarity function
- similarity measure
- similarity measures
- similarity score
- similarity scores
- slot
- subgraph
- syntactic variation
- target word
- technique
- terms
- textual entailment
- thesaurus
- tokens
- training
- training set
- tree
- trees
- user
- verb
- web corpus
- word
- word form
- word level
- wordnet
- words
