基于FPGA的事件抽取模型与加速器的设计实现

Event extraction technology is important to achieve the quickly extraction of specific information, and it can be widely used in information retrieval, sentiment analysis and other scenarios. Chinese event extraction is more difficult than English event extraction due to the characteristics of Chinese language. Based on the state of the art English event extraction neural network model, a CEE DGCNN (Chinese Event Extraction based on multi layer Dilate Gated Convolutional Neural Network) is proposed, which is suitable for hardware implementation. CEE DGCNN achieves 71.71% F1 score of trigger classification on the ACE2005 Chinese corpus. The accelerator of CEE DGCNN is designed and implemented, and the model size is further optimized by quantization. The accelerator can achieve 97 GOP/s on the Xilinx XCKU115 FPGA, which is 67 times faster than CPU.     

基于移动设备的移动身份认证服务方案设计

将结合智能卡认证、动态口令认证和无线PKI认证,提出一种电子商务中的基于移动设备的移动身份认证服务方案,以统一接口服务的形式,支持多种应用业务的接入。     

面向事件检测的预训练主动学习模型

深度学习在事件检测任务上取得了显著的成果,但模型严重依赖于大量的标注数据. 由于事件结构化的信息和丰富的标签表示,使得获取注释的成本很高,难以大量获得. 针对事件检测任务,为了提高语料标注效率,减少训练过程所需的标注样本数量,提出一种联合主动学习和预训练模型的事件检测模型. 针对主动学习模型存在的冷启动问题,设计了基于融合不确定性的特殊样本选择策略,估计样本在微调下游事件检测任务方面的潜在贡献. 一方面,结合预训练模型从原始任务中带来的丰富的语义信息,避免了重新设计网络结构或从零开始训练; 另一方面,利用主动学习选择信息丰富的样本能更好地微调预训练模型,减少数据标注成本. 在ACE 2005语料上进行数值实验验证,结果证明了所提出的EDPAL算法的有效性.