Convolutional Gated Recurrent Units for Medical Relation Classification
This work addresses relation extraction for medical professionals, but it is incremental as it combines existing CNN and RNN techniques.
The paper tackled medical relation classification in clinical records by proposing a unified CNN and bidirectional GRU architecture, achieving significantly better performance than previous single-model methods on two datasets.
Convolutional neural network (CNN) and recurrent neural network (RNN) models have become the mainstream methods 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 significantly better than previous single-model methods on both datasets.