Why “dark thoughts” aren't really dark: A novel algorithm for metaphor identification

Opposition theory and computational semiotics

“…As argued quite recently by Veale (2011: 278; our emphasis) "… while computationally interesting, none (of these models) has yet achieved the scalability or robustness needed to make a signifi cant practical impact outside the laboratory. " However, recent cognitively motivated algorithms (Turney et al 2011;Assaf et al 2013;Neuman et al 2013) have shown that metaphor identifi cation is feasible and may have important consequences for natural language understanding.…”

“…Krishnakumaran, Zhu 2007), we restrict the scope of this paper to metaphoric usages involving nouns and to adjective-noun metaphors only. We focus on this type of metaphor as recent advances in natural language processing (Turney et al 2011;Assaf et al 2013) have led to signifi cant advancements in identifying this type of metaphor and to high correlation with human performance.…”

Measuring metaphoricity

“…Wilks (1978) used selectional restrictions for this purpose; Mason (2004) used hand-crafted knowledge resources to detect similar selectional mismatches; another approach is to detect selectional mismatches using statistically created resources (e.g., Shutova & Sun, 2013). A second general approach to the binary classification problem has been to use mismatches in properties like abstractness (Gandy, et al, 2013;Assaf, et al, 2013;Tsvetkov, et al, 2013;Turney, et al, 2011), semantic similarity (Li & Sporleder, 2010;Sporleder & Li, 2010), and domain membership (Dunn, 2013a(Dunn, , 2013b to identify metaphoric units of language. A third approach has been to use forms of topic modelling to identify linguistic units which represent both a metaphoric topic and a literal topic (Strzalkowski, 2013;Bracewell, et al, 2013;Mohler, et al, 2013).…”

Multi-dimensional abstractness in cross-domain mappings

“…The study of cognitive metaphor processes has largely focused on content-specific representations of such mappings within a number of content domains, such as TIME and IDEAS. Thus, a crossdomain mapping may be represented as something like ARGUMENT IS WAR. Computational approaches to metaphor, however, have represented cross-domain mappings using higher-level properties like abstractness (Gandy, et al, 2013;Assaf, et al, 2013;Tsvetkov, et al, 2013;Turney, et al, 2011), semantic similarity (Li & Sporleder, 2010;Sporleder & Li, 2010), domain membership (Dunn, 2013a(Dunn, , 2013b, word clusters that represent semantic similarity Shutova & Sun, 2013), and selectional preferences (Wilks, 1978;Mason, 2004). Most of these approaches rely on some concept of abstractness, whether directly (e.g., in terms of abstractness ratings) or indirectly (e.g., in terms of clusters containing abstract words).…”