Improving RNN with A ention and Embedding for Adverse Drug Reactions

ABSTRACT

We add our embedding framework to a bi-directional long short-term memory (Bi-LSTM) neural network, and further study the e ect of using attention weights in neural networks for sequence labelling tasks to extract knowledge of Adverse Drug Reactions(ADR).

跨过上下文窗口以形成最接近的上下文向量将更好地指示标签之间的关系。 我们使用RNN之上的注意力机制来输出在每个步骤中生成的注意力权重。

Bi-Directional Recurrent Neural Network with Attention (RNNA)

输入是一个sentence

RESULTS