Graph Convolution for Multimodal Information Extraction from Visually Rich Documents

no code implementations • NAACL 2019 • Xiaojing Liu, Feiyu Gao, Qiong Zhang, Huasha Zhao

In VRDs, visual and layout information is critical for document understanding, and texts in such documents cannot be serialized into the one-dimensional sequence without losing information.

document understanding Entity Extraction using GAN