Re-run experimental datasets are in /data/. with codes in /code/.

For your own datasets, please run /code/data_preprocessing for extensional knowledge generation

If you use our codes, please cite:

@inproceedings{zhu2024edentail, title={EDEntail: An Entailment-based Few-shot Text Classification with Extensional Definition}, author={Zhu, Zixiao and Qian, Junlang and Feng, Zijian and Zhou, Hanzhang and Mao, Kezhi}, booktitle={Findings of the Association for Computational Linguistics: NAACL 2024}, pages={1124--1137}, year={2024} }