Precisely Predicting Acute Kidney Injury with Convolutional Neural Network Based on Electronic Health Record Data

no code implementations • 27 May 2020 • Yu Wang, Junpeng Bao, JianQiang Du, Yongfeng Li

Compared with the existing AKI predictors, the predictor in this work greatly improves the precision of early prediction of AKI by using the Convolutional Neural Network architecture and a more concise input vector.

Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning

no code implementations • 19 Apr 2020 • Hongcai Xu, Junpeng Bao, Gaojie Zhang

This paper proposes a dynamic Knowledge graph-based dialogue generation method with improved adversarial Meta-Learning (KDAD).

Adversarial Attack Dialogue Generation +1

Knowledge-graph based Proactive Dialogue Generation with Improved Meta-Learning

no code implementations • 19 Apr 2020 • Hongcai Xu, Junpeng Bao, Junqing Wang

To overcome this drawback, we propose a knowledge graph based proactive dialogue generation model (KgDg) with three components, improved model-agnostic meta-learning algorithm (MAML), knowledge selection in knowledge triplets embedding, and knowledge aware proactive response generator.

Dialogue Generation Knowledge Graphs +4