Metaphor Detection with Effective Context Denoising
This work addresses metaphor detection, a specific NLP task, with incremental improvements in performance.
The paper tackles metaphor detection by proposing RoPPT, a RoBERTa-based model that uses target-oriented parse trees to focus on semantically relevant information, achieving state-of-the-art results on multiple datasets.
We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection. Compared to existing models, RoPPT focuses on semantically relevant information and achieves the state-of-the-art on several main metaphor datasets. We also compare our approach against several popular denoising and pruning methods, demonstrating the effectiveness of our approach in context denoising. Our code and dataset can be found at https://github.com/MajiBear000/RoPPT