In this paper, we propose FrameBERT, a RoBERTa-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection. FrameBERT not only achieves better or comparable performance to the state-of-the-art, but also is more explainable and interpretable compared to existing models, attributing to its ability of accounting for external knowledge of FrameNet.
@article{arxiv.2302.04834,
title = {FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning},
author = {Yucheng Li and Shun Wang and Chenghua Lin and Frank Guerin and Loïc Barrault},
journal= {arXiv preprint arXiv:2302.04834},
year = {2023}
}