FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning
This addresses metaphor detection in natural language processing, offering improved interpretability for applications like text analysis, but it is incremental as it builds on existing models and frameworks.
The paper tackled concept-level metaphor detection by proposing FrameBERT, a RoBERTa-based model that learns FrameNet embeddings, achieving better or comparable performance to state-of-the-art methods while being more explainable.
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.