Recent advances in neural metaphor processing: A linguistic, cognitive and social perspective

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4673–4686 June 6–11, 2021. ©2021 Association for Computational Linguistics 4673 Recent advances in neural metaphor processing: A linguistic, cognitive and social perspective Xiaoyu Tong♣, Ekaterina Shutova♣, Martha Lewis♦♣ ♣ILLC, University of Amsterdam, the Netherlands ♦Department of Engineering Mathematics, University of Bristol, United Kingdom xiaoyu.tong@student.uva.nl, e.shutova@uva.nl, martha.lewis@bristol.ac.uk Abstract Metaphor is an indispensable part of hu- man cognition and everyday communication. Much research has been conducted elucidating metaphor processing in the mind/brain and the role it plays in communication. In recent years, metaphor processing systems have benefited greatly from these studies, as well as the rapid advances in deep learning for natural language processing (NLP). This paper provides a com- prehensive review and discussion of recent de- velopments in automated metaphor processing, in light of the findings about metaphor in the mind, language, and communication, and from the perspective of downstream NLP tasks. 1 Introduction Metaphor is a figurative device that allows us to por- tray one domain, often abstract, in terms of another that is typically more concrete (Lakoff and Johnson, 1980). In the sentences His eyes lightened at the news, or Her mood darkened, the abstract domain of emotion is described in terms of the more con- crete domain of brightness. Through cross-domain associations and comparisons, metaphor enables us to communicate complex abstract concepts, to convey our affective states, to reinforce our argu- ments and, ultimately, to forge entirely novel word meanings. Metaphor is also ubiquitous in language, occuring on average in every three sentences, ac- cording to corpus-linguistic research (Steen et al., 2010b; Shutova, 2011). This makes accurate in- terpretation of metaphorical language essential for many NLP tasks and applications. A systematic and comprehensive survey of metaphor processing systems was published five years ago (Shutova, 2015). Since then, automated metaphor processing has shifted focus towards neu- ral approaches and there has been much activity in the area, including two shared tasks (Leong et al., 2018, 2020). The development has kept pace with the development of deep learning techniques, and the state-of-the-art performance has been advanced very quickly, stressing the need for a new survey focusing on this recent progress. Moreover, the design and evaluation of metaphor processing systems should be informed by both the cognition of metaphor and its role in commu- nication, as well as the potential applications of these systems. It is common practice in the NLP community to divide metaphor processing into two sub-tasks, metaphor identification and interpreta- tion, and the two shared tasks encourage the use of a common task definition and particular metaphor corpora for the development of metaphor identi- fication systems. However, there has been little discussion about whether or how well the existing systems address theoretical and cognitive consider- ations in the use of metaphor and how insights and models produced by this work could inform and benefit the wider natural language understanding (NLU) research. This paper aims to provide a starting …

Content truncated to 500 words