Creative Language Retrieval: A Robust Hybrid of Information Retrieval and Linguistic Creativity

Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, pages 278–287, Portland, Oregon, June 19-24, 2011. c⃝2011 Association for Computational Linguistics Creative Language Retrieval: A Robust Hybrid of Information Retrieval and Linguistic Creativity Tony Veale School of Computer Science and Informatics, University College Dublin, Belfield, Dublin D4, Ireland. Tony.Veale@UCD.ie Abstract Information retrieval (IR) and figurative language processing (FLP) could scarcely be more different in their treatment of lan- guage and meaning. IR views language as an open-ended set of mostly stable signs with which texts can be indexed and re- trieved, focusing more on a text’s potential relevance than its potential meaning. In contrast, FLP views language as a system of unstable signs that can be used to talk about the world in creative new ways. There is another key difference: IR is prac- tical, scalable and robust, and in daily use by millions of casual users. FLP is neither scalable nor robust, and not yet practical enough to migrate beyond the lab. This pa- per thus presents a mutually beneficial hy- brid of IR and FLP, one that enriches IR with new operators to enable the non-literal retrieval of creative expressions, and which also transplants FLP into a robust, scalable framework in which practical applications of linguistic creativity can be implemented. 1 Introduction Words should not always be taken at face value. Figurative devices like metaphor can communicate far richer meanings than are evident from a super- ficial – and perhaps literally nonsensical – reading. Figurative Language Processing (FLP) thus uses a variety of special mechanisms and representations, to assign non-literal meanings not just to meta- phors, but to similes, analogies, epithets, puns and other creative uses of language (see Martin, 1990; Fass, 1991; Way, 1991; Indurkhya, 1992; Fass, 1997; Barnden, 2006; Veale and Butnariu, 2010). Computationalists have explored heterodox solutions to the procedural and representational challenges of metaphor, and FLP more generally, ranging from flexible representations (e.g. the preference semantics of Wilks (1978) and the col- lative semantics of Fass (1991, 1997)) to processes of cross-domain structure alignment (e.g. structure mapping theory; see Gentner (1983) and Falken- hainer et al. 1989) and even structural inversion (Veale, 2006). Though thematically related, each approach to FLP is broadly distinct, giving com- putational form to different cognitive demands of creative language: thus, some focus on inter- domain mappings (e.g. Gentner, 1983) while oth- ers focus more on intra-domain inference (e.g. Ba- rnden, 2006). However, while computationally interesting, none has yet achieved the scalability or robustness needed to make a significant practical impact outside the laboratory. Moreover, such systems tend to be developed in isolation, and are rarely designed to cohere as part of a larger frame- work of creative reasoning (e.g. Boden, 1994). In contrast, Information Retrieval (IR) is both scalable and robust, and its results translate easily from the laboratory into practical applications (e.g. see Salton, 1968; Van Rijsbergen, 1979). Whereas FLP derives its utility and its fragility from its at- tempts to identify deeper meanings beneath …

Content truncated to 500 words