It’s not Rocket Science: Interpreting Figurative Language in Narratives

It’s not Rocket Science: Interpreting Figurative Language in Narratives Tuhin Chakrabarty1∗ Yejin Choi2,3 Vered Shwartz4∗ 1Columbia University, USA 2Allen Institute for Artificial Intelligence, USA 3Paul G. Allen School of Computer Science & Engineering, University of Washington, USA 4University of British Columbia, Canada tuhin.chakr@cs.columbia.edu, yejinc@allenai.org, vshwartz@cs.ubc.ca Abstract Figurative language is ubiquitous in English. Yet, the vast majority of NLP research focuses on literal language. Existing text representa- tions by design rely on compositionality, while figurative language is often non- compositional. In this paper, we study the interpretation of two non-compositional fig- urative languages (idioms and similes). We collected datasets of fictional narratives con- taining a figurative expression along with crowd-sourced plausible and implausible con- tinuations relying on the correct interpretation of the expression. We then trained models to choose or generate the plausible contin- uation. Our experiments show that models based solely on pre-trained language mod- els perform substantially worse than humans on these tasks. We additionally propose knowledge-enhanced models, adopting human strategies for interpreting figurative language types: inferring meaning from the context and relying on the constituent words’ literal meanings. The knowledge-enhanced models improve the performance on both the discrim- inative and generative tasks, further bridging the gap from human performance. 1 Introduction Figurative language is a medium for mak- ing language expressive, communicating ab- stract ideas otherwise difficult to visualize, and provoking emotions (Roberts and Kreuz, 1994; Fussell and Moss, 1998). Despite the ubiquity of figurative language across various forms of speech and writing, the vast majority of NLP research fo- cuses primarily on literal language. Figurative language is often more challenging due to its implicit nature and is seen as ‘‘a bottleneck in automatic text understanding’’ (Shutova, 2011). ∗Work done at the Allen Institute for AI. In recent years, transformer-based language models (LMs) achieved substantial performance gains across various NLP tasks, however, they still struggle with figurative language. In particular, one of the challenges is that figurative expres- sions are often non-compositional, that is, the phrase meaning deviates from the literal mean- ings of its constituents. For instance, the idiom ‘‘chicken feed’’ in Figure 1 denotes ‘‘a ridicu- lously small sum of money’’ instead of ‘‘food for poultry’’. By design, transformer-based LMs compute a word representation as a function of the representation of its context. LM-based phrase representations encode the meanings of the constituent words but hardly capture any mean- ing that is introduced by the composition itself (Yu and Ettinger, 2020). Even though LMs may recognize when a word is used non-literally, and potentially attend to it less, they still struggle to represent the implied, non-literal meaning of such phrases (Shwartz and Dagan, 2019). While LMs potentially memorize familiar id- ioms, we can expect them to further struggle with similes, which are often created ad hoc (Carston and Wearing, 2011). For example, in Figure 1, the person is compared to ‘‘a high mountain lake without a wind stirring it’’ to imply calmness. Many such figurative expressions com- pose in a non-trivial way, and introduce implicit meaning that …

Content truncated to 500 words