Extracting mentions of Adverse Drug Reaction (ADR) from biomedical texts, aiming to support pharmacovigilance and drug safety surveillance, remains a challenging task as many ADR mentions are nested, discontinuous and overlapping. To solve these issues, in this paper, we propose a deep neural model for Complex Adverse Drug Reaction Mentions Extraction, called DeepCADRME. It first transforms the ADR mentions extraction problem as an N-level tagging sequence. Then, it feeds the sequences to an N-level model based on contextual embeddings where the output of the pre-trained model of the current level is used to build a new deep contextualized representation for the next level. This allows the DeepCADRME system to transfer knowledge between levels. Experimental results performed on the TAC 2017 ADR dataset, show the effectiveness of DeepCADRME which leads to a new state-of-the-art performance by reaching a F1 of 85.35% and 85.41% with and without mention types, respectively. The evaluation results also highlight the benefits of exploring language model to effectively extract different types of ADR mentions.

从生物医学文献中提取不良药物反应（ADR）的内容，旨在支持药物警戒和药物安全性监视，仍然是一项艰巨的任务，因为许多ADR内容是嵌套，不连续和重叠的。为了解决这些问题，在本文中，我们提出了一个深刻的神经模型Ç omplex一个dverse d地毯[R反应的影响中号entions Ëxtraction，称为DeepCADRME。它首先将ADR提及的提取问题转换为N级标记序列。然后，它基于上下文嵌入将序列提供给N层模型，其中使用当前层的预训练模型的输出来为下一层构建新的深层上下文表示。这允许DeepCADRME系统在各个级别之间传递知识。在TAC 2017 ADR数据集上进行的实验结果表明，DeepCADRME的有效性导致F1达到85.35％和85.41％，分别提及和不提及类型，从而带来了新的最新性能。评估结果还强调了探索语言模型以有效提取不同类型的ADR提及的好处。