模型:
microsoft/xdoc-base
XDoc是一个统一的预训练模型,可以处理不同的文档格式。 XDoc模型只需36.7%的参数,在下游任务中实现了可比或更好的性能,这对实际部署来说是具有成本效益的。
XDoc: Unified Pre-training for Cross-Format Document Understanding Jingye Chen, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei, EMNLP 2022
如果您认为XDoc对您有帮助,请引用我们:
@article{chen2022xdoc, title={XDoc: Unified Pre-training for Cross-Format Document Understanding}, author={Chen, Jingye and Lv, Tengchao and Cui, Lei and Zhang, Cha and Wei, Furu}, journal={arXiv preprint arXiv:2210.02849}, year={2022} }