conftrace_

2023 EACL EACL 2023

Metaphor Detection with Effective Context Denoising

Abstract

AbstractWe 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.

Authors

Shun Wang, Yucheng Li, Chenghua Lin, Loic Barrault, Frank Guerin

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Machine Learning > Core Methods > Representation Learning Machine Learning > Learning Types > Self-Supervised Learning

Keywords

transfer learning semantic parsing metaphor detection context denoising

More from EACL 2023

All EACL 2023 papers →

BLM-AgrF: A New French Benchmark to Investigate Generalization of Agreement in Neural Networks

Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining

Unsupervised Anomaly Detection in Multi-Topic Short-Text Corpora

Low-Resource Compositional Semantic Parsing with Concept Pretraining

Made of Steel? Learning Plausible Materials for Components in the Vehicle Repair Domain

Self-Adapted Utterance Selection for Suicidal Ideation Detection in Lifeline Conversations