How to Make a Frenemy: Multitape FSTs for Portmanteau Generation

Human Language Technologies: The 2015 Annual Conference of the North American Chapter of the ACL, pages 206–210, Denver, Colorado, May 31 – June 5, 2015. c⃝2015 Association for Computational Linguistics How to Make a Frenemy: Multitape FSTs for Portmanteau Generation Aliya Deri and Kevin Knight Information Sciences Institute Department of Computer Science University of Southern California {aderi, knight}@isi.edu Abstract A portmanteau is a type of compound word that fuses the sounds and meanings of two component words; for example, “frenemy” (friend + enemy) or “smog” (smoke + fog). We develop a system, including a novel mul- titape FST, that takes an input of two words and outputs possible portmanteaux. Our sys- tem is trained on a list of known portmanteaux and their component words, and achieves 45% exact matches in cross-validated experiments. 1 Introduction Portmanteaux are new words that fuse both the sounds and meanings of their component words. In- novative and entertaining, they are ubiquitous in ad- vertising, social media, and newspapers (Figure 1). Some, like “frenemy” (friend + enemy), “brunch” (breakfast + lunch), and “smog” (smoke + fog), ex- press such unique concepts that they permanently enter the English lexicon. Portmanteau generation, while seemingly trivial for humans, is actually a combination of two com- plex natural language processing tasks: (1) choos- ing component words that are both semantically and phonetically compatible, and (2) blending those words into the final portmanteau. An end-to-end system that is able to generate novel portmanteaux Figure 1: A New Yorker headline portmanteau. W1 W2 PM affluence influenza affluenza anecdote data anecdata chill relax chillax flavor favorite flavorite guess estimate guesstimate jogging juggling joggling sheep people sheeple spanish english spanglish zeitgeist ghost zeitghost Table 1: Valid component words and portmanteaux. with minimal human intervention would be not only a useful tool in areas like advertising and journalism, but also a notable achievement in creative NLP. Due to the complexity of both component word selection and blending, previous portmanteau gen- eration systems have several limitations. The Neho- vah system (Smith et al., 2014) combines words only at exact grapheme matches, making the generation of more complex phonetic blends like “frenemy” or “brunch” impossible. ¨Ozbal and Strappavara (2012) blend words phonetically and allow inexact matches but rely on encoded human knowledge, such as sets of similar phonemes and semantically related words. Both systems are rule-based, rather than data-driven, and do not train or test their systems with real-world portmanteaux. In contrast to these approaches, this paper presents a data-driven model that accomplishes (2) by blending two given words into a portmanteau. That is, with an input of “friend” and “enemy,” we want to generate “frenemy.” 206 F1 R1 EH3 N3 D4 EH3 N3 AH5 M5 IY5 T1 OW1 F1 UW3 T2 ER3 K5 IY5 Figure 2: Derivations for friend + enemy → “frenemy” and tofu + turkey → “tofurkey.” Subscripts indicate the step applied to each phoneme. We take a statistical modeling approach to port- manteau generation, using training examples (Table 1) to learn weights for …

Content truncated to 500 words