Named Entity Recognition (NER) is a challenging task that extracts named entities from unstructured text data, including news, articles, social comments, etc. The NER system has been studied for decades. Recently, the development of Deep Neural Networks and the progress of pre-trained word embedding have become a driving force for NER. Under such circumstances, how to make full use of the information extracted by word embedding requires more in-depth research. In this paper, we propose an Adversarial Trained LSTM-CNN (ASTRAL) system to improve the current NER method from both the model structure and the training process. In order to make use of the spatial information between adjacent words, Gated-CNN is introduced to fuse the information of adjacent words. Besides, a specific Adversarial training method is proposed to deal with the overfitting problem in NER. We add perturbation to variables in the network during the training process, making the variables more diverse, improving the generalization and robustness of the model. Our model is evaluated on three benchmarks, CoNLL-03, OntoNotes 5.0, and WNUT-17, achieving state-of-the-art results. Ablation study and case study also show that our system can converge faster and is less prone to overfitting.

命名实体识别（NER）是一项具有挑战性的任务，它从非结构化文本数据（包括新闻，文章，社会评论等）中提取命名实体。NER系统已经研究了数十年。近年来，深度神经网络的发展和预训练词嵌入的发展已成为NER的驱动力。在这种情况下，如何充分利用词嵌入提取的信息需要进行更深入的研究。在本文中，我们提出了一种对抗训练的LSTM-CNN（ASTRAL）系统，以从模型结构和训练过程两个方面改进当前的NER方法。为了利用相邻词之间的空间信息，引入门控CNN融合相邻词的信息。除了，针对神经网络中的过拟合问题，提出了一种具体的对抗训练方法。我们在训练过程中对网络中的变量增加了扰动，使变量更加多样化，从而提高了模型的泛化性和鲁棒性。我们的模型在三个基准（CoNLL-03，OntoNotes 5.0和WNUT-17）上进行了评估，从而获得了最新的结果。消融研究和案例研究还表明，我们的系统可以收敛得更快，并且不太容易过度拟合。