Simple Models for Word Formation in Slang

Proceedings of NAACL-HLT 2018, pages 1424–1434 New Orleans, Louisiana, June 1 - 6, 2018. c⃝2018 Association for Computational Linguistics Simple Models for Word Formation in English Slang Vivek Kulkarni Department of Computer Science University of California, Santa Barbara vvkulkarni@cs.ucsb.edu William Yang Wang Department of Computer Science University of California, Santa Barbara william@cs.ucsb.edu Abstract We propose generative models for three types of extra-grammatical word formation phenom- ena abounding in English slang: Blends, Clip- pings, and Reduplicatives. Adopting a data- driven approach coupled with linguistic knowl- edge, we propose simple models with state of the art performance on human annotated gold standard datasets. Overall, our models reveal insights into the generative processes of word formation in slang – insights which are increas- ingly relevant in the context of the rising preva- lence of slang and non-standard varieties on the Internet. 1 Introduction Linguistic analysis of slang has traditionally re- ceived little attention with some arguing that re- search on slang be assigned to an “extra-linguistic darkness” (Labov, 1972). However, Eble (2012) argues that the emergence of social media has pre- dominantly increased the usage of slang and non standard forms and “slang is now worldwide the vo- cabulary of choice of young people”1. This increas- ing pervasiveness has recently motivated research on slang and the linguistic phenomena it manifests. Most notable are the works of (Mattiello, 2005, 2008, 2013), who argues that slang exhibits extra- grammatical properties that distinguish it from the standard form. Specifically, linguistic phenomena like alpha- betisms, blending, clippings, and reduplicatives abound in slang (see Table 1)2. Note the rich and varied word formation patterns ranging from simple abbreviations like dink to more com- plex combinations like lambortini, a blend of lamborghini and martini. Note further, that 1While the definition of slang is a controversial issue, we adopt a broad definition including non-standard expressions. 2While such phenomena are likely present in several lan- guages, in this work we restrict ourselves to slang in English. Word Derived From Type dink double income no kids alphabetism lambortini lamborghini + martini blend diamat dialectical + materialism blend tude attitude clipping (fore) brill brilliant clipping (back) yik-yak yik reduplicative Table 1: Sample words depicting word formation in slang. Note the rich variation across different types. even within a particular class like BLENDS there are variations in what portions of the components are retained. These word formation mechanisms are not only attractive from a linguistic standpoint in deepening our understanding of slang but also have applica- tions spanning the development of rich conversa- tional agents and tools like brand name generators ( ¨Ozbal and Strapparava, 2012). While such phe- nomena have been qualitatively studied by Mat- tiello (2008, 2013), computational models for their generation have not been proposed. In this paper, we propose the first simple mod- els for generating blends, clippings, and reduplica- tives3. Our models incorporate linguistic insights coupled with data-driven analysis to model the above phenomena. In line with “Occam’s razor”, we strive for simplicity. The simplicity of our mod- els …

Content truncated to 500 words