Authors: Zhenrong Zhang, Lei Jiang, Youhui Guo, Jianshu Zhang, Jun Du
Affiliation: University of Science and Technology of China (USTC), iFLYTEK AI Research
Description: 1. We use the UniLM and LiLT as decoder to utilize text and layout information, OCR results with manual-rule sorting are fed into decoder to predict target.
2. We assemble DocPrompt, UniLM and LiLT.