Improving Document Image Understanding with Reinforcement Finetuning

Nguyen, Bao-Sinh1, Le, Dung Tien1, Vu, Hieu M.1, Nguyen, Tuan-Anh D.1, Nguyen, Minh-Tien1,2, Le, Hung3

Tóm tắt

Successful Artificial Intelligence systems often require numerous labeled data to extract information from document images. In this paper, we investigate the problem of improving the performance of Artificial Intelligence systems in understanding document images,...