ID 原文 译文
45536 传统突发话题发现方法无法解决社交网络短文本稀疏性问题，并需要复杂的后处理过程。 The traditional method of bursty topic discovery cannot solve the sparseness problem in social network, and require complicated post-processing.
45537 为了解决上述问题，提出一种基于循环神经网络（RNN, recurrent neural network）和主题模型的突发话题发现（RTM-SBTD）方法。 In order to tackle this problem, a bursty topic discovery method based on recurrent neural network and topic model was proposed.
45538 首先，综合 RNN 和逆序文档频率（IDF, inverse document frequency）构建权重先验来学习词的关系， Firstly, the weight prior based on RNN and IDF were constructed to learn the relationship between words.
45539 同时通过构建词对解决短文本稀疏性问题。 At the same time, the word pairs were constructed to solve the sparseness problem.
45540 其次，模型中引入针板先验（spike and slab）来解耦突发话题分布的稀疏和平滑。 Secondly, the “spike and slab” prior was introduced to decouple the sparsity and smoothness of the bursty topic distribution.
45541 最后，引入词的突发性来区分建模普通话题和突发话题，实现突发话题自动发现。 Finally, the burstiness of words were leveraged to model the bursty topic and the common topic, and automatically discover thebursty topics.
45542 实验结果表明与现有的主流突发话题发现方法相比，所提 RTM-SBTD 方法在多种评价指标上优于对比算法。 Various experiments were conducted: both qualitative and quantitative evaluations demonstrate that the proposed RTM-SBTD method outperforms favorably against several state-of-the-art methods.
45543 在 IaaS 平台中，虚假数据的存在将对测评结果造成混淆，无法为用户给出公平公正的平台选择依据。 The interference of false or fake test data on IaaS platform will contaminate the evaluation results, confusingusers’ choices for IaaS services.
45544 针对该问题，提出一种适用于 IaaS 平台的测试代理 agent 保护机制（APM, agent protection mechanism）， To solve this problem, an agent protection mechanism (APM) for IaaS platform test environment was proposed.
45545 在不需要额外软硬件支持的条件下保证 agent 的完整性和命令执行的正确性； It ensured the integrity and commanded validity of the agent without additional hardware or software.