FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning

2023/02/09 by Yucheng Li, Shun Wang, Li, Yucheng +7 · 3 citations
Computer Science · Psychology · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Language, Metaphor, and Cognition #Natural Language Processing Techniques

paper · pdf · doi:10.48550/arxiv.2302.04834

openalex publication_date 2023/02/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Mechanistic Interpretability of Socio-Political Frames in Language Models
• The Medical Metaphors Corpus (MCC)
• Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders

Related

• MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories
• Adversarial Multi-task Learning for End-to-end Metaphor Detection
• Metaphor Generation with Conceptual Mappings
• Metaphor Detection with Effective Context Denoising
• Enhancing Metaphor Detection through Soft Labels and Target Word Prediction