Proceedings of the Workshop on Figurative Language Processing

Abstract

Poetry is known for its novel expression using figurative language. We introduce a writing task that contains the essential challenges of generating meaningful figurative language and can be evaluated. We investigate how to find metaphorical connections between abstract themes and concrete domains by asking people to write four-line poems on a given metaphor, such as "death is a rose" or "anger is wood". We find that only 24% of poems successfully make a metaphorical connection. We present five alternate ways people respond to the prompt and release our dataset of 186 categorized poems. We suggest opportunities for computational approaches. 1haf. 2017. Accelerating innovation through analogy mining. CoRR, abs/1706.05585. Justine Kao and Dan Jurafsky. 2012. A computational analysis of style, affect, and imagery in contemporary poetry. In Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature, pages 8-17. David M Kaplan and David M Blei. 2007. A computational approach to style in american poetry.

Testing the role of metadata in metaphor identification

“…In computational linguistics, a great amount of recent work has been concerned with addressing the challenge of identifying metaphors in texts. This is evident in the series of four Workshops on Metaphor in NLP from 2013 to 2016 and in the two Workshops on Figurative Language Processing in 2018 (Beigman Klebanov et al, 2018b) and 2020 (Leong et al, 2020), each of which involved a shared task (ST) in automatic metaphor detection. Identification systems that achieved the best results in the first shared task relied on neural networks incorporating long-term short-term memory (LSTM) architectures (see Mu et al, 2019 for a discussion).…”