Abstract
We propose a new model for metaphor detection in which an expectation component estimates representations of expected word meanings in a given context, whereas a realization component computes representations of target word meanings in context. We also introduce a systematic evaluation methodology that estimates generalization performance in three settings: within distribution, a new strong out of distribution setting, and a novel out-of-pretraining setting. Across all settings, the expectation-realization model obtains results that are competitive with or better than previous metaphor detection models.- Anthology ID:
- 2024.figlang-1.11
- Volume:
- Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico (Hybrid)
- Editors:
- Debanjan Ghosh, Smaranda Muresan, Anna Feldman, Tuhin Chakrabarty, Emmy Liu
- Venues:
- Fig-Lang | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 79–84
- Language:
- URL:
- https://preview.aclanthology.org/remove-affiliations/2024.figlang-1.11/
- DOI:
- 10.18653/v1/2024.figlang-1.11
- Cite (ACL):
- Oseremen Uduehi and Razvan Bunescu. 2024. An Expectation-Realization Model for Metaphor Detection. In Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024), pages 79–84, Mexico City, Mexico (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- An Expectation-Realization Model for Metaphor Detection (Uduehi & Bunescu, Fig-Lang 2024)
- PDF:
- https://preview.aclanthology.org/remove-affiliations/2024.figlang-1.11.pdf