This repository contains the implementation of our ACL 2023 paper "Metaphor Detection via Explicit Basic Meanings Modelling" (https://arxiv.org/pdf/2305.17268.pdf).
BasicBERT is a novel metaphor identification mechanism that leverages the Metaphor Identification Process (MIP) via direct basic meaning modelling of targets. The core idea behind BasicBERT is to compare the contextual meaning of a word with its basic meaning to identify metaphorical usages. This approach significantly improves the metaphor detection performance, as demonstrated in our paper.
We're preparing our code and pre-trained models. Will be ready soon. In the mean time, you could check out our work at EACL 2023, where we provide a ready-to-use metaphor detection model that can be easily applied on your own data.
This project is licensed under the MIT License.
If you find this code useful in your research, please consider citing our paper:
@article{Li2023MetaphorDV,
title={Metaphor Detection via Explicit Basic Meanings Modelling},
author={Yucheng Li and Shunyu Wang and Chenghua Lin and Guerin Frank},
journal={ArXiv},
year={2023},
volume={abs/2305.17268}
}
For questions about our paper or code, please open an issue.