Convolutional Gated Recurrent Units for Medical Relation Classification

Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have become the mainstream architectures for relation classification. We propose a unified architecture, which exploits the advantages of CNN and RNN simultaneously, to identify medical relations in clinical records, with only word embedding features. Our model learns phrase-level features through a CNN layer, and these feature representations are directly fed into a bidirectional gated recurrent unit (GRU) layer to capture long-term feature dependencies. We evaluate our model on two clinical datasets, and experiments demonstrate that our model performs better than previous single-model methods on both datasets.