Compressive Sensing
Compressive Sensing
复制标题
DOI：
10.1007/978-981-13-2523-6_1
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
L. Kong;Bowen Wang;Guihai Chen
中科院分区：
文献类型：
--
作者：
L. Kong;Bowen Wang;Guihai Chen
为了获得高质量和大规模的标记数据用于信息安全研究，我们提出了一种新的方法，将生成对抗网络与BiLSTM-Attention-CRF模型相结合，从人群注释中获得标记数据。我们使用生成式对抗网络来寻找群体注释中的共同特征，然后将它们与领域词典特征和句子依赖特征结合起来，作为额外的特征引入BiLSTM-Attention-CRF模型，然后用于进行众包中的命名实体识别。最后，我们创建一个数据集，使用信息安全数据来评估我们的模型。实验结果表明，我们的模型具有更好的性能比其他基线模型。
In order to obtain high quality and large‐scale labelled data for information security research, we propose a new approach that combines a generative adversarial network with the BiLSTM‐Attention‐CRF model to obtain labelled data from crowd annotations. We use the generative adversarial network to find common features in crowd annotations and then consider them in conjunction with the domain dictionary feature and sentence dependency feature as additional features to be introduced into the BiLSTM‐Attention‐CRF model, which is then used to carry out named entity recognition in crowdsourcing. Finally, we create a dataset to evaluate our models using information security data. The experimental results show that our model has better performance than the other baseline models.