Paper Info
Title
Unsupervised recognition of literal and non-literal use of idiomatic expressions
Abstract
We propose an unsupervised method for distinguishing literal and non-literal usages of idiomatic expressions. Our method determines how well a literal interpretation is linked to the overall cohesive structure of the discourse. If strong links can be found, the expression is classified as literal, otherwise as idiomatic. We show that this method can help to tell apart literal and non-literal usages, even for idioms which occur in canonical form.
Year
Venue
Keywords
2009
EACL
non-literal usage,overall cohesive structure,unsupervised recognition,unsupervised method,strong link,literal interpretation,non-literal use,canonical form,idiomatic expression
Field
DocType
Citations 
Expression (mathematics),Computer science,Canonical form,Natural language processing,Artificial intelligence
Conference
34
PageRank 
References 
Authors
1.88
15
2
Name
Order
Citations
PageRank
Caroline Sporleder145331.84
Linlin Li21177.66