Literal and Metaphorical Senses in Compositional Distributional Semantic Models
نویسندگان
چکیده
Metaphorical expressions are pervasive in natural language and pose a substantial challenge for computational semantics. The inherent compositionality of metaphor makes it an important test case for compositional distributional semantic models (CDSMs). This paper is the first to investigate whether metaphorical composition warrants a distinct treatment in the CDSM framework. We propose a method to learn metaphors as linear transformations in a vector space and find that, across a variety of semantic domains, explicitly modeling metaphor improves the resulting semantic representations. We then use these representations in a metaphor identification task, achieving a high performance of 0.82 in terms of F-score.
منابع مشابه
The Mental Representation of Polysemy across Word Classes
Experimental studies on polysemy have come to contradictory conclusions on whether words with multiple senses are stored as separate or shared mental representations. The present study examined the semantic relatedness and semantic similarity of literal and non-literal (metonymic and metaphorical) senses of three word classes: nouns, verbs, and adjectives. Two methods were used: a psycholinguis...
متن کاملConventionalization of Lexical Meanings and the Role of Metaphoricity: Processing of Metaphorical Polysemy Using a Cross-modal Lexical Priming Task*
Decades of lexical ambiguity research has rigorously studied effects of relative sense frequency on sense disambiguation in biased contexts, while fundamental semantic issues such as distinction of different types of ambiguities, or influences from lexical meanings’ semantic nature (e.g., literal or metaphorical) as well as these meanings’ degrees of conventionalization, have received less atte...
متن کاملTypology of Adjectives Benchmark for Compositional Distributional Models
In this paper we present a novel application of compositional distributional semantic models (CDSMs): prediction of lexical typology. The paper introduces the notion of typological closeness, which is a novel rigorous formalization of semantic similarity based on comparison of multilingual data. Starting from the Moscow Database of Qualitative Features for adjective typology, we create four dat...
متن کاملDynamic and Static Prototype Vectors for Semantic Composition
Compositional Distributional Semantic methods model the distributional behavior of a compound word by exploiting the distributional behavior of its constituent words. In this setting, a constituent word is typically represented by a feature vector conflating all the senses of that word. However, not all the senses of a constituent word are relevant when composing the semantics of the compound. ...
متن کاملAutomatic Acquisition of Knowledge About Multiword Predicates
Human interpretation of natural language relies heavily on cognitive processes involving metaphorical and idiomatic meanings. One area of computational linguistics in which such processes play an important, but largely unaddressed, role is the determination of the properties of multiword predicates (MWPs). MWPs such as give a groan and cut taxes involve metaphorical meaning extensions of highly...
متن کامل