In order to obtain high quality and large-scale labelled data for information security research, we propose a new approach that\ncombines a generative adversarial network with the BiLSTM-Attention-CRF model to obtain labelled data fromcrowd annotations.\nWe use the generative adversarial network to find common features in crowd annotations and then consider them in conjunction\nwith the domain dictionary feature and sentence dependency feature as additional features to be introduced into the BiLSTMAttention-\nCRF model, which is then used to carry out named entity recognition in crowdsourcing. Finally, we create a dataset to\nevaluate our models using information security data.The experimental results show that our model has better performance than\nthe other baseline models.
Loading....