College of Computer, National University of Defense Technology, Changsha, China.
College of Computer, National University of Defense Technology, Changsha, China.
J Biomed Inform. 2019 Nov;99:103290. doi: 10.1016/j.jbi.2019.103290. Epub 2019 Sep 23.
Clinical named entity recognition (CNER), which intends to automatically detect clinical entities in electronic health record (EHR), is a committed step for further clinical text mining. Recently, more and more deep learning models are used to Chinese CNER. However, these models do not make full use of the information in EHR, for these models are either word-based or character-based. In addition, neural models tend to be locally unstable and even tiny perturbation may mislead them. In this paper, we firstly propose a novel adversarial training based lattice LSTM with a conditional random field layer (AT-lattice LSTM-CRF) for Chinese CNER. Lattice LSTM is used to capture richer information in EHR. As a powerful regularization method, AT can be used to improve the robustness of neural models by adding perturbations to the training data. Then, we conduct experiments on the proposed neural model with dataset of CCKS-2017 Task 2. The results show that the proposed model achieves a highly competitive performance (with an F1 score of 89.64%) compared to other prevalent neural models, which can be a reinforced baseline for further research in this field.
临床命名实体识别（CNER）旨在自动检测电子健康记录（EHR）中的临床实体，是进一步进行临床文本挖掘的重要步骤。最近，越来越多的深度学习模型被用于中文 CNER。然而，这些模型并没有充分利用 EHR 中的信息，因为这些模型要么基于单词，要么基于字符。此外，神经模型往往不太稳定，即使微小的干扰也可能误导它们。在本文中，我们首先提出了一种新颖的基于对抗训练的格 LSTM 与条件随机场层（AT-lattice LSTM-CRF）的中文 CNER 方法。格 LSTM 用于捕获 EHR 中的更丰富信息。作为一种强大的正则化方法，AT 可以通过向训练数据中添加扰动来提高神经模型的鲁棒性。然后，我们在 CCKS-2017 任务 2 的数据集上对所提出的神经模型进行了实验。结果表明，与其他流行的神经模型相比，所提出的模型具有很高的竞争力（F1 得分达到 89.64%），可以作为该领域进一步研究的强化基准。
