AI-DRIVEN AUTOMATIC DETECTION OF METAPHORS AND IDIOMS IN ENGLISH
Keywords:
Metaphor detection; Idiom identification; Figurative language; NLP; Deep learning; Large Language Models; Cognitive linguistics.Abstract
This study explores AI-driven approaches for automatically detecting metaphors and idioms in English by integrating linguistic theories with modern NLP technologies. It highlights how frameworks such as MIP, SPV, and Cognitive Metaphor Theory support the identification of figurative expressions in context. The paper analyzes the evolution from rule-based methods to deep learning and Large Language Models that achieve high accuracy in figurative-language classification. Remaining challenges and future directions, including contextual understanding and embodied cognition, are also discussed.
Downloads
References
Automatic Metaphor Detection using Large-Scale Lexical Resources and Conventional Metaphor Extraction Yorick Wilks, Adam Dalton, James Allen, Lucian Galescu (2013) https://aclanthology.org/W13-0905/
Cross-Lingual Metaphor Detection Using Common Semantic Features Yulia Tsvetkov, Elena Mukomel, Anatole Gershman (2013) https://aclanthology.org/W13-0906/
MIss RoBERTa WiLDe: Metaphor Identification Using Masked Language Model with Wiktionary Lexical Definitions
Applied Sciences (2022) https://doi.org/10.3390/app12042081
A Systematic Review of Figurative Language Detection: Methods, Challenges, and Multilingual Perspectives Natural Language Processing Journal (2025) https://www.sciencedirect.com/science/article/pii/S2949719125000688
Methods of Annotating and Identifying Metaphors in the Field of Natural Language Processing Martina Ptiček & Jasminka Dobša (2023) https://doi.org/10.3390/fi15060201
Metaphor Detection with Context Enhancement and Curriculum Learning Kaidi Jia & Rongsheng Li (NAACL 2024) https://aclanthology.org/2024.naacl-long.149/
