School of Software Engineering, South China University of Technology, Guangzhou, China; Key Laboratory of Big Data and Intelligent Robot (South China University of Technology), Ministry of Education, Guangzhou, China.
Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London, United Kingdom.
Neural Netw. 2021 Jun;138:68-77. doi: 10.1016/j.neunet.2020.12.027. Epub 2020 Dec 31.
The success of neural network based methods in named entity recognition (NER) is heavily relied on abundant manual labeled data. However, these NER methods are unavailable when the data is fully-unlabeled in a new domain. To address the problem, we propose an unsupervised cross-domain model which leverages labeled data from source domain to predict entities in unlabeled target domain. To relieve the distribution divergence when transferring knowledge from source to target domain, we apply adversarial training. Furthermore, we design an entity-aware attention module to guide the adversarial training to reduce the discrepancy of entity features between different domains. Experimental results demonstrate that our model outperforms other methods and achieves state-of-the-art performance.
基于神经网络的命名实体识别 (NER) 方法的成功在很大程度上依赖于大量的手动标记数据。然而，当新领域中的数据完全未标记时，这些 NER 方法就不可用了。为了解决这个问题，我们提出了一种无监督跨域模型，该模型利用源域中的标记数据来预测未标记目标域中的实体。为了缓解从源域向目标域传递知识时的分布差异，我们应用对抗训练。此外，我们设计了一个实体感知注意力模块来引导对抗训练，以减少不同域之间实体特征的差异。实验结果表明，我们的模型优于其他方法，达到了最新的性能水平。
