Abstract
We implement an innovative strategy for metaphor identification and interpretation in texts using three different GPT OpenAI models. Metaphors are a very frequent cognitive and linguistic resource, pervasive in multiple types of human communication, singularly in discourse. Due to their conceptual and formal complexity, they are difficult to detect, classify and process. Methods of analysis have been often manual in spite of a large body of methodological proposals for computer metaphor processing. Even manual approaches pose serious challenges for highly trained annotators. Our purpose is to conduct a preliminary experiment to measure precision in identification and interpretation of metaphors in Spanish verbs analyzed in a set of corpus concordances. We implemented the method in a group of 10 polysemous Spanish verbs, in which at least one of the meanings is metaphorical. We ran three experiments with ChatGPT-4o and ChatGPT4-Turbo. We tested the precision of the models against a human annotated dataset of 1511 corpus contexts taken from the Verbario database. Results show precision between 85.18% and 88.29%, with one of the verbs achieving 94.47%. The best model is ChatGPT4-Turbo with precision between 82.61% and 94.47%. Explanations generated by the models are aligned with the identification task and show logic, complexity and specificity. The method is simple to implement and achieves high precision in comparison with traditional methods for metaphor detection and interpretation. Further research may include replicating the experiment with an expanded dataset, different data or additional and more complex tasks such as conceptual metaphor analysis.


Similar content being viewed by others
Data Availability
Not applicable.
References
Lakoff G, Johnson M. Metaphors we live by. Chicago: University of Chicago Press; 1980.
Kövecses Z. Extended conceptual metaphor theory. Cambridge: Cambridge University Press; 2020.
Geeraerts D. Theories of lexical semantics. Oxford: Oxford University Press; 2009.
Hanks P. The syntagmatics of metaphor and idiom. Int J Lexicogr. 2004;17(3):245–74.
Hanks P. Metaphoricity is gradable. In: Stefanowitsch A, Gries ST, editors. Corpus-based approaches to metaphor and metonymy. Berlin: Mouton de Gruyter; 2006. p. 17–35.
Ježek E. The lexicon. An introduction. Oxford: Oxford University Press; 2016.
Pustejovsky J, Batiukova O. The lexicon. Cambridge: Cambridge University Press; 2019.
Hanks P. Lexical analysis: norms and exploitations. Cambridge: The MIT Press; 2013.
Barnden JA. Metaphor and artificial intelligence. In: Gibbs RW, editor. The Cambridge handbook of metaphor and thought. Cambridge: Cambridge University Press; 2008. p. 311–38.
Pragglejaz G. MIP: a method for identifying metaphorically used words in discourse. Metaphor Symb. 2007;22(1):1–39.
Steen GJ, Dorst AG, Herrmann JB, Kaal A, Krennmayr T, Pasma T. A method for linguistic metaphor identification: from MIP to MIPVU. Amsterdam: John Benjamins Publishing Company; 2010.
Ge M, Mao R, Cambria E. A survey on computational metaphor processing techniques: from identification, interpretation, generation to application. Artif Intell Rev. 2023;56(S2):1829–95.
Rai S, Chakraverty S. A survey on computational metaphor processing. ACM Comput Surv. 2020;53(2):1–37.
Tong X, Shutova E, Lewis M. Recent advances in neural metaphor processing: a linguistic, cognitive and social perspective. In: Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies. Association for Computational Linguistics; 2021. p. 4713–4726.
Haddad AH, Premasiri D, Ranasinghe T, Mitkov R. Deep learning methods for extracting metaphorical names of flowers and plants. Proces Leng Natl. 2023;71:261–71.
Steen GJ. Slowing metaphor down: elaborating deliberate metaphor theory. Amsterdam: John Benjamins Publishing Company; 2023.
Barcelona A. Metaphor and metonymy at the crossroads: a cognitive perspective. Berlin: De Gruyter; 2003.
Lakoff G. The contemporary theory of metaphor. In: Ortony A, editor. Metaphor and thought. Cambridge: Cambridge University Press; 1993. p. 202–51.
Lakoff G. The neural theory of metaphor. In: Gibbs RW, editor. The Cambridge handbook of metaphor and thought. Cambridge: Cambridge University Press; 2008. p. 17–38.
Lakoff G, Turner M. More than cool reason: a field guide to poetic metaphor. Chicago: University of Chicago Press; 1987.
Semino E, Demjén Z, Hardie A, Payne S, Rayson P. Metaphor, cancer and the end of life: a corpus-based study. Abingdon-on-Thames: Routledge; 2018.
Renau I. Using verb patterns to find recurrent metaphors in corpus. In: Mitits L, Kiosses S, editors. Lexicography for inclusion: proceedings of the 19th EURALEX international congress, 7–9 September 2021, Alexandroupolis, Vol. 2. Alexandroupolis: Democritus University of Thrace; 2021. p. 673–682.
Wilks Y. A preferential, pattern-seeking, semantics for natural language inference. Artif Intell. 1975;6(1):53–74.
Deignan A. Metaphor and corpus linguistics. Amsterdam: John Benjamins Publishing Company; 2005.
Miller GA. WordNet: an electronic lexical database. Cambridge: MIT Press; 1998.
Rojo G. Introducción a la lingüística de corpus en español. Abingdon-on-Thames: Routledge; 2021.
McEnery T, Hardie A. Corpus linguistics: method, theory and practice. Cambridge: Cambridge University Press; 2012.
Brown TB, Mann B, Ryder N, et al. Language models are few-shot learners. In: Advances in neural information processing systems. vol. 33. Curran Associates; 2020. p. 1877–1901.
Renau I, Nazar R, Castro A, López B, Obreque J. Verbo y contexto de uso: Un análisis basado en corpus con métodos cualitativos y cuantitativos. Rev Sign. 2019;52(101):878–901.
Hanks P. Corpus pattern analysis. In: Williams G, Vessier S, editors. Proceedings of the 11th EURALEX international congress. Lorient: Université de Bretagne-Sud; 2004. p. 87–97.
DiMuccio-Failla P, Giacomini L. Investigating semi-automatic procedures in pattern-based lexicography. In: Kosem I, Kuhn TZ, Correia M, Ferreira JP, Janssen M, Pereira I, et al., editors. Electronic lexicography in the 21st century: smart lexicography. Proceedings of the eLex 2019 conference. Lexical Computing; 2019. p. 490–505.
Renau I, Nazar R.: Verbario. https://www.verbario.com/.
Semino E. Metaphor in discourse. Cambridge: Cambridge University Press; 2008.
Funding
I. Renau has been funded by Project Fondecyt Regular nr. 1231594. Project ESMAS-ES+ (PID2022-137170OB-I00) funded by MCIN/AEI//FEDER “Una manera de hacer Europa”. E. Puraivan has been partially funded by the Escuela de Ingeniería Informática, Universidad de Valparaíso, Chile, through grant No. 01.016/2020 and Beca de Doctorado Nacional ANID 21232242.
Author information
Authors and Affiliations
Contributions
All authors have contributed equally to the development of the manuscript and the critical review of the final content.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Research involving human and/or animals
Not applicable.
Informed consent
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Puraivan, E., Renau, I. & Riquelme, N. Metaphor Identification and Interpretation in Corpora with ChatGPT. SN COMPUT. SCI. 5, 976 (2024). https://doi.org/10.1007/s42979-024-03331-0
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-024-03331-0