method: result of zhang2023-03-19

Authors: zhang jianan

Affiliation: AliCloud

Description: My main idea is: through the given training set, produce a lot of mock data and expand the amount of training data. Then the LiLT model is trained and the final result is obtained.

Jiapeng Wang et al. “LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding” (2023).