Black Holes and White Rabbits: Metaphor Identification with Visual Features

Proceedings of NAACL-HLT 2016, pages 160–170, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Black Holes and White Rabbits: Metaphor Identification with Visual Features Ekaterina Shutova Computer Laboratory University of Cambridge es407@cam.ac.uk Douwe Kiela Computer Laboratory University of Cambridge dk427@cam.ac.uk Jean Maillard Computer Laboratory University of Cambridge jean@maillard.it Abstract Metaphor is pervasive in our communication, which makes it an important problem for nat- ural language processing (NLP). Numerous approaches to metaphor processing have thus been proposed, all of which relied on linguis- tic features and textual data to construct their models. Human metaphor comprehension is, however, known to rely on both our lin- guistic and perceptual experience, and vision can play a particularly important role when metaphorically projecting imagery across do- mains. In this paper, we present the first metaphor identification method that simulta- neously draws knowledge from linguistic and visual data. Our results demonstrate that it outperforms linguistic and visual models in isolation, as well as being competitive with the best-performing metaphor identification methods, that rely on hand-crafted knowledge about domains and perception. 1 Introduction Metaphor lends vividness, sophistication and clar- ity to our thought and communication. At the same time, it plays a fundamental structural role in our cognition, helping us to organise and project knowledge (Lakoff and Johnson, 1980; Feldman, 2006). Metaphors arise due to systematic associ- ations between distinct, and seemingly unrelated, concepts. For instance, when we talk about “the turning wheels of a political regime”, “rebuilding the campaign machinery” or “mending foreign pol- icy”, we view politics and political systems in terms of mechanisms, they can function, break, be mended etc. The existence of this association allows us to transfer knowledge and imagery from the domain of mechanisms (the source domain) to that of po- litical systems (the target domain). According to Lakoff and Johnson (1980), such metaphorical map- pings, or conceptual metaphors, form the basis of metaphorical language. Metaphor is pervasive in our communication, which makes it important for NLP applications deal- ing with real-world text. A number of approaches to metaphor processing have thus been proposed, us- ing supervised classification (Gedigian et al., 2006; Mohler et al., 2013; Tsvetkov et al., 2013; Hovy et al., 2013; Dunn, 2013a), clustering (Shutova et al., 2010; Shutova and Sun, 2013), vector space models (Shutova et al., 2012; Mohler et al., 2014), lexical resources (Krishnakumaran and Zhu, 2007; Wilks et al., 2013) and web search with lexico- syntactic patterns (Veale and Hao, 2008; Li et al., 2013; Bollegala and Shutova, 2013). So far, these and other metaphor processing works relied on tex- tual data to construct their models. Yet, several experiments indicated that perceptual properties of concepts, such as concreteness and imageability, are important features for metaphor identification (Tur- ney et al., 2011; Neuman et al., 2013; Gandy et al., 2013; Strzalkowski et al., 2013; Tsvetkov et al., 2014). However, all of these methods used manually-annotated linguistic resources to deter- mine these properties (such as the MRC concrete- ness database (Wilson, 1988)). To the …

Content truncated to 500 words