模型:
hfl/chinese-electra-base-discriminator
请在重新训练这些模型时,使用ElectraForPreTraining作为辨别器,使用ElectraForMaskedLM作为生成器。
Google和斯坦福大学发布了一个名为ELECTRA的新预训练模型,与BERT及其变种相比,该模型大小更紧凑,性能相对竞争力更强。为了进一步加快中文预训练模型的研究速度,哈工大与科大讯飞联合实验室已基于ELECTRA的官方代码发布了中文ELECTRA模型。相比BERT及其变种,ELECTRA-small只有1/10的参数量,却可以在多个NLP任务上获得相似甚至更高的分数。
该项目基于ELECTRA的官方代码: https://github.com/google-research/electra
您可能还感兴趣:
更多HFL提供的资源: https://github.com/ymcui/HFL-Anthology
如果您发现我们的资源或论文有用,请考虑在您的论文中包含以下引用。
@inproceedings{cui-etal-2020-revisiting, title = "Revisiting Pre-Trained Models for {C}hinese Natural Language Processing", author = "Cui, Yiming and Che, Wanxiang and Liu, Ting and Qin, Bing and Wang, Shijin and Hu, Guoping", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.findings-emnlp.58", pages = "657--668", }