tailieunhanh - Báo cáo khoa học: "Unsupervised Recognition of Literal and Non-Literal Use of Idiomatic Expressions"

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. | Unsupervised Recognition of Literal and Non-Literal Use of Idiomatic Expressions Caroline Sporleder and Linlin Li Saarland University Postfach 15 11 50 66041 Saarbriicken Germany csporled linlin @ 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. 1 Introduction Texts frequently contain expressions whose meaning is not strictly literal such as metaphors or idioms. Non-literal expressions pose a major challenge to natural language processing as they often exhibit lexical and syntactic idiosyncrasies. For example idioms can violate selectional restrictions as in push one s luck under the assumption that only concrete things can normally be pushed disobey typical subcategorisation constraints . in line without a determiner before line or change the default assignments of semantic roles to syntactic categories . in break sth with X the argument X would typically be an instrument but for the idiom break the ice it is more likely to fill a patient role as in break the ice with Russia . To avoid erroneous analyses a natural language processing system should recognise if an expression is used non-literally. While there has been a lot of work on recognising idioms see Section 2 most previous approaches have focused on a typebased classification dividing expressions into idiom or not an idiom irrespective of their actual use in a discourse context. However while some expressions such as by and large always have a non-compositional idiomatic meaning many idioms such as break the ice or spill the beans share their linguistic form with perfectly literal .