Automatic generating the clinically accurate radiology report from X-ray images is important but challenging. The identification of multi-grained abnormal regions in image and corresponding abnormalities is difficult for data-driven neural models. In this work, we introduce a Memory-aligned Knowledge Graph (MaKG) of clinical abnormalities to better learn the visual patterns of abnormalities and their relationships by integrating it into a deep model architecture for the report generation. We carry out extensive experiments and show that the proposed MaKG deep model can improve the clinical accuracy of the generated reports.

Automatic generating financial report from a set of news is important but challenging. The financial reports is composed of key points of the news and corresponding inferring and reasoning from specialists in financial domain with professional knowledge. The challenges lie in the effective learning of the extra knowledge that is not well presented in the news, and the misalignment between topic of input news and output knowledge in target reports. In this work, we introduce a disentangled variational topic inference approach to learn two latent variables for news and report, respectively. We use a publicly available dataset to evaluate the proposed approach. The results demonstrate its effectiveness of enhancing the language informativeness and the topic accuracy of the generated financial reports.