Semantically Informed Slang Interpretation

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5213 - 5231 July 10-15, 2022 ©2022 Association for Computational Linguistics Semantically Informed Slang Interpretation Zhewei Sun1, Richard Zemel1,2,4, Yang Xu1,3,4 1Department of Computer Science, University of Toronto, Toronto, Canada 2Department of Computer Science, Columbia University, New York, USA 3Cognitive Science Program, University of Toronto, Toronto, Canada 4Vector Institute for Artificial Intelligence, Toronto, Canada {zheweisun, zemel, yangxu}@cs.toronto.edu Abstract Slang is a predominant form of informal lan- guage making flexible and extended use of words that is notoriously hard for natural lan- guage processing systems to interpret. Ex- isting approaches to slang interpretation tend to rely on context but ignore semantic exten- sions common in slang word usage. We pro- pose a semantically informed slang interpreta- tion (SSI) framework that considers jointly the contextual and semantic appropriateness of a candidate interpretation for a query slang. We perform rigorous evaluation on two large-scale online slang dictionaries and show that our ap- proach not only achieves state-of-the-art accu- racy for slang interpretation in English, but also does so in zero-shot and few-shot sce- narios where training data is sparse. Further- more, we show how the same framework can be applied to enhancing machine translation of slang from English to other languages. Our work creates opportunities for the automated interpretation and translation of informal lan- guage. 1 Introduction Slang is one of the most common forms of infor- mal language, but interpreting slang can be difficult for both humans and machines. Empirical studies have shown that, although it is done instinctively, interpretation and translation of unfamiliar or novel slang expressions can be quite hard for humans (Braun and Kitzinger, 2001; Mattiello, 2009). Sim- ilarly, slang interpretation is also notoriously diffi- cult for state-of-the-art natural language processing (NLP) systems, which presents a critical challenge to downstream applications such as natural lan- guage understanding and machine translation. Consider the sentence “I got really steamed when my car broke down”. As illustrated in Fig- ure 1, directly applying a translation system such as Google Translate on this raw English sentence would result in a nonsensical translation of the Figure 1: Illustrations of slang interpretation in English (top panel) and slang translation (bottom panel) from English to French on the original sentence (nonsensi- cal), or on the interpreted version of the sentence (sen- sical). slang term steamed in French. This error is due partly to the underlying language model that fails to recognize the flexible extended use of the slang term from its conventional meaning (e.g., “vapor”) to the slang meaning of “angry”. However, if knowledge about such semantic extensions can be incorporated into interpreting the slang prior to translation, as Figure 1 shows the system would be quite effective in translating the intended meaning. Here we consider the problem of slang inter- pretation illustrated in the top panel of Figure 1. Given a target slang term like steamed in a novel query sentence, we want to automatically …

Content truncated to 500 words