ID	原文	译文
4503	最后，根据威胁发生概率确定网络安全威胁严重度，结合威胁影响度计算威胁态势值以获取网络威胁态势。	Finally, the severity of the network security threat was determined according to the probability of threat occurrence, and the threat situation valuewas calculated according to the threat impact to obtain the network threat situation.
4504	仿真实验结果表明，所提方法对网络威胁具有较强的表征能力，能够有效直观地评估网络威胁的整体态势。	The simulation results show that the proposed method has strong characterization ability for network threats, and can effectively and intuitively evaluate theoverall situation of network threat.
4505	针对 Android 操作系统 App 内第三方域名采集用户信息造成的隐私泄露问题，基于 TF-IDF 模型和层次聚类方法提出了移动设备中的隐私泄露评估方案 HostRisk。	Aiming at the privacy leakage, which was caused by collecting user information by third-party host in Androidoperating system App, a privacy leakage evaluation scheme HostRisk was proposed. HostRisk was based on TF-IDF modeland hierarchical clustering method, which was applied in mobile device.
4506	TF-IDF 模型通过 App 内域名的行为特征计算域名与App 的业务相关性，对于未能表现出 App 业务相关性行为特征的业务相关域名通过平均连接的凝聚型层次聚类方法进行调整优化，最终根据 App 内所有域名的排名计算其隐私泄露危害程度。	The TF-IDF model calculated the business relev-ance between Apps and hosts via the behavior characteristics of the hosts in these Apps. For the business related hosts thatfail to express the business relevance characteristics, those hosts were adjusted and optimized via the average connected hie-rarchical agglomerative clustering method. Finally, the harmful degree of privacy leakage was evaluated based on the rank-ing of all hosts in the App.
4507	实验结果验证了所提方案的有效性和效率。	The experimental results verify the effectiveness and efficiency of the scheme.
4508	针对信息安全领域内的共指消解问题，提出了一个混合型方法。	To solve the problem of coreference resolution in information security, a hybrid method was proposed.
4509	该方法在原来 BiLSTM-attention-CRF 模型的基础上引入领域词典匹配机制，将其与文档层面的注意力机制相结合，	Based on the BiLSTM-attention-CRF model, the domain-dictionary matching mechanism was introduced and combined with the attention mechanism at the document level.
4510	作为一种新的基于字典的注意力机制，来解决从文本中提取候选词时对稀有实体以及长度较长的实体识别能力稍弱的问题，	As a new dictionary-based attention mechanism, the word features werecalculated to solve the problem of weak recognition ability of rare entities and entities with long length when extracting candidates from text.
4511	并通过总结领域文本特征，将提取出的待消解候选词根据词性分别采用规则与机器学习的方式进行消解，以提高准确性。	And by summarizing the features of the domain texts, the candidates were coreferenced by rules andmachine learning according to the part of speech to improve the accuracy.
4512	通过在安全领域数据集的实验，分别从共指消解以及提取候选词并分类 2 个方面证明了方法的优越性。	Through the experiments on security data set,the superiority of the method is proved from the aspects of coreference resolution and extraction of candidates from text .