Self-Attention based Network for Medical Query Expansion

The aim of clinical decision support implementing electronic health records is to satisfy the physicians' information needs. We are motivated to propose a self-attention based network on query expansion. Considering the difficulty and cost of medical text annotation and inspired by the idea of migration learning, we choose the Semantic Textual Similarity dataset for model training. Different from the previous work, the proposed approach is not only considering the score of a single term as an expansion term, but also taking the score of term combination into account. Our model utilizes Convolutional Neural Networks (CNN) to obtain sentence representation and self-attention mechanism for entity representation. With self-attention, it is able to estimate the weight of each entity to learn better representation for all entities. We conduct the experiments on three standard datasets of Text REtrieval Conference Clinical Decision Support Track, where the approach has a promising overall performance over the strong baselines.