Search

Existing pharmaceutical information extraction research often focus on standalone entity or relationship identification tasks over drug instructions. There is a lack of a holistic solution for drug knowledge extraction. Moreover, current methods perform poorly in extracting fine-grained interaction relations from drug instructions. To solve these problems, this paper proposes an information extraction framework for drug instructions. The framework proposes deep learning models with fine-tuned pre-training models for entity recognition and relation extraction, in addition, it incorporates an novel entity pair calibration process to promote the performance for fine-grained relation extraction. The framework experiments on more than 60k Chinese drug description sentences from 4000 drug instructions. Empirical results show that the framework can successfully identify drug related entities (F1 ≥ 0.95) and their relations (F1 ≥ 0.83) from the realistic dataset, and the entity pair calibration plays an important role (~5% F1 score improvement) in extracting fine-grained relations.

In this paper, the boundary value problem for the integro-differential equation with a small parameter ε>0: $$\left\{ {\begin{array}{*{20}c} {\varepsilon ^2 x'' = f(t,T_1 x, \cdot \cdot \cdot ,T_m x,x,\varepsilon ),} \\ {\alpha _i x(i,\varepsilon ) - ( - 1)^i \beta _i x'(i,\varepsilon ) = A_i (\varepsilon ),i = 0,1} \\ \end{array} } \right.$$ is discussed, whereT′is are integral operators defined onC[0,1]: $$T_i :g(t) \to T_i g{\text{ = }}\varphi _{\text{i}} (t,\varepsilon ) + \int_0^t {K_i } (t,\xi ,\varepsilon )g(\xi )d\xi .$$ Using the differential inequality technique, the existence of solutions is proved and the estimate of solutions is obtained as well. In particular, this result applied to the high-order (n≥3) boundary value problem for ordinary differential equations with a small parameter ε>0: $$\left\{ {\begin{array}{*{20}c} {\varepsilon ^2 y^{(n)} = f(t,y,y', \cdot \cdot \cdot ,y^{(n - 2)} ,\varepsilon ),} \\ {y^{(j)} (0,\varepsilon ) = \alpha _j (\varepsilon ),j = 0,1, \cdot \cdot \cdot ,n - 3,} \\ {\alpha _i y^{^{(n - 2)} } (i,\varepsilon ) - ( - 1)^i \beta _i y^{(n - 1)} (i,\varepsilon ) = A_i (\varepsilon ),i = 0,1.} \\ \end{array} } \right.$$