ID	原文	译文
1953	不同类型对象在异质网络中的重要程度不同，它们在相似度学习过程中的发挥的作用也不同。	Different types of objects have different degrees of importance in heterogeneous networks, and play differentroles in the similarity learning process.
1954	针对异质网络，提出了一种基于节点影响力的相似度度量方法 NISim，	This paper proposes a node influence based similarity measure method (NISim)het-erogeneous information network.
1955	该模型既考虑了网络中的链接结构，也保留了网络中的语义信息，同时区分不同类型节点对异质网络的作用。	This method not only considers the link structure in network but also keeps the semantic in-formation in heterogeneous networks. Also, this method distinguishes the effect to heterogeneous network brought by differ-ent types of nodes.
1956	在异质信息网络环境下，通过启发式规则区分并量化不同类型节点的影响力权值，并结合网络链接结构和节点间语义关系，解决了提高相似度学习准确性的问题。	In heterogeneous network, the heuristic rules are used to distinguish and quantify the influence weight of different types of nodes. In addition, the link structure in network and the semantic relationship are combined to solve the problem of improving similarity learning accuracy.
1957	实验结果表明，该方法能够有效地对异质信息网络不同类型节点进行相似度度量，可以应用在网络搜索、推荐系统以及知识图谱构建等不同领域。	Experimental results show that this method can measure the similarity be-tween different types of nodes effectively. It can be applied in different fields such as network search, recommendation sys-tem and knowledge graph construction and so on.
1958	提出了一种主瓣灵巧干扰环境下的盲距离-角度联合估计方法，可有效对抗主瓣灵巧干扰(MainlobeSmart Jamming，MSJ)并提取目标回波的距离-角度联合参数信息。	A blind range-direction estimation method is proposed for suppressing the mainlobe smart jamming(MSJ). The proposed method can effectively suppress the MSJ and estimate the direction-distance parameter of the targe techo.
1959	新方法首先利用阵元级数据进行盲源分离(BlindSource Separation，BSS)，分离目标回波和干扰，同时可得到信源混合矩阵的估计。	Firstly, the target and MSJ is separated by the blind source separation (BSS)algorithm with the element data, and the estimation of the mixed matrix can be obtained simultaneously.
1960	然后根据主瓣灵巧干扰在某一角度上表现为多个回波信号，而目标只有一个回波这一先验信息来鉴别目标和主瓣灵巧干扰，由此可以估计目标的距离参数。	Secondly, according to the prior information that the MSJcontains multiple false target echoes in a certain direction, while the real target just contains one echo, we can determine the separated channel which contains the real target. In this way, the real target distance parameter can be estimated.
1961	最后，由上述的鉴别结果得到对应目标的混合矩阵的列矢量，其包含了目标导向矢量信息，据此可估计目标的空间角度参数。	Finally, the mixed matrix column vector of the real target is obtained by the above judgement, which can be adopted to estimate the di-rection parameter of the real target.
1962	仿真结果表明，新方法可以至少有效对抗 2 个主瓣灵巧干扰，且可同时得到较高的目标距离-角度估计精度。	Simulation results show that the proposed method can effectively suppress two MSJs atleast, and obtain good range-direction estimation performance at the same time.