ERNIE (Enhanced Representation through kNowledge IntEgration) is proposed by Baidu in 2019,
which is designed to learn language representation enhanced by knowledge masking strategies i.e. entity-level masking and phrase-level masking.
Experimental results show that ERNIE achieve state-of-the-art results on five Chinese natural language processing tasks including natural language inference,
semantic similarity, named entity recognition, sentiment analysis and question answering.
This released pytorch model is converted from the officially released PaddlePaddle ERNIE model and
a series of experiments have been conducted to check the accuracy of the conversion.
1from transformers import AutoTokenizer, AutoModel
2tokenizer = AutoTokenizer.from_pretrained("nghuyong/ernie-1.0-base-zh")
3model = AutoModel.from_pretrained("nghuyong/ernie-1.0-base-zh")
1@article{sun2019ernie,
2 title={Ernie: Enhanced representation through knowledge integration},
3 author={Sun, Yu and Wang, Shuohuan and Li, Yukun and Feng, Shikun and Chen, Xuyi and Zhang, Han and Tian, Xin and Zhu, Danxiang and Tian, Hao and Wu, Hua},
4 journal={arXiv preprint arXiv:1904.09223},
5 year={2019}
6}
