Clinical Named Entity Recognition (CNER) aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translational research. In recent years, deep neural networks have achieved significant success in named entity recognition and many other Natural Language Processing (NLP) tasks. Most of these algorithms are trained end to end, and can automatically learn features from large scale labeled datasets. However, these data-driven methods typically lack the capability of processing rare or unseen entities. Previous statistical methods and feature engineering practice have demonstrated that human knowledge can provide valuable information for handling rare and unseen cases. In this paper, we address the problem by incorporating dictionaries into deep neural networks for the Chinese CNER task. Two different architectures that extend the Bi-directional Long Short-Term Memory (Bi-LSTM) neural network and five different feature representation schemes are proposed to handle the task. Computational results on the CCKS-2017 Task 2 benchmark dataset show that the proposed method achieves the highly competitive performance compared with the state-of-the-art deep learning methods.

Designing intelligent slippery surfaces for droplet manipulation is critical for many applications from drug delivery to bio‐analysis, while is of great challenging in sustainability for inescapable wastage of lubricant layer. Herein, an ultrafast lubricant self‐mediating (self‐replenishing/‐absorbing) photothermal slippery surface is designed that achieves sustainable transport of droplet under the irradiation of near infrared light (NIL) even if the lubricant layer is wiped clean completely, as well as at other man‐made extreme conditions. The ultrafast lubricant self‐mediating performance is caused by synergistic effects of interconnection of porous structure and photothermal expansion of the material. When lubricant on surface is lost, photothermal expansion of material can quickly squeeze the lubricant inside the base to flow into and out of the interconnected porous structure to generate a fresh lubricant layer. Attractively, when the NIL is turned off, the rebuilt lubricant layer can be swiftly self‐absorbed into the porous to inhibit unnecessary wastage. Moreover, an arbitrary split of droplet in desired configurations can be achieved by controlling the NIL irradiating route. This sustainable droplet manipulation induced by ultrafast lubricant self‐mediating can be extensively applied in microfluidics and micro‐reactor settings.

No abstract

No abstract

No abstract