FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning

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

2/9/2023

cs.CL

No official code found. Best implementation: liyucheng09/MetaphorFrame (39 stars, last commit 2023-11-25).

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.

View on arXiv View PDF

Code Implementations(1)

liyucheng09/MetaphorFrameCommunity100%

FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning. Presented at EACL 2023.

395Shell, PythonOct 28, 20212 years ago

deep-learningmachine-learningmetaphor-detection

Similar Papers

ContrastWSD: Enhancing Metaphor Detection with Word Sense Disambiguation Following the Metaphor Identification Procedure

91% match2023

An Expectation-Realization Model for Metaphor Detection

88% match2023

Metaphor Detection with Effective Context Denoising

87% match2023

Metaphor Detection via Explicit Basic Meanings Modelling

86% match1 repo42023

Enhancing Metaphor Detection through Soft Labels and Target Word Prediction

85% match2024

A Match Made in Heaven: A Multi-task Framework for Hyperbole and Metaphor Detection

85% match2023

Cite this paper

@article{li2023framebert,
  title  = {FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning},
  author = {Yucheng Li and Shun Wang and Chenghua Lin and Frank Guerin and Loïc Barrault},
  year   = {2023},
  eprint = {2302.04834},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.04834v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/2302.04834.svg)](https://codeofpaper.com/paper/2302.04834)