To find out all dependency relationships in which metaphors probably exist between syntax constituents in a given sentence,a dependency tree matching algorithm oriented to Chinese metaphor processing is proposed based...To find out all dependency relationships in which metaphors probably exist between syntax constituents in a given sentence,a dependency tree matching algorithm oriented to Chinese metaphor processing is proposed based on a research of unordered tree inclusion matching.In this algorithm,the pattern library is composed of formalization dependency syntax trees that are derived from large-scale metaphor sentences.These kinds of metaphor sentences are saved in the pattern library in advance.The main process of this algorithm is up-down searching and bottom-up backtracking revising.The algorithm discovers potential metaphoric structures in Chinese sentences from metaphoric dependency pattern library.Finally,the feasibility and efficiency of the new matching algorithm are further testified by the results of a series of experiments on dependency pattern library.Hence,accurate dependency relationships can be achieved through this algorithm.展开更多
智能环境传统的规则推理机制中,网关内布置的推理机从各种传感器中获取推理所需数据并与规则库相匹配,承担整个推理工作.本文利用Rete算法将规则构建为推理网络,并结合雾计算的概念将Rete推理节点分配至环境内配置的智能节点中协同推理...智能环境传统的规则推理机制中,网关内布置的推理机从各种传感器中获取推理所需数据并与规则库相匹配,承担整个推理工作.本文利用Rete算法将规则构建为推理网络,并结合雾计算的概念将Rete推理节点分配至环境内配置的智能节点中协同推理以减轻网关负载,由此推理节点的分配成为关键,分配不合理将导致资源利用不平衡及响应延迟.本文利用活动影响下规则触发的规律设计了活动聚类算法CoA(Clustering of Activities)对活动聚类后分别建立其推理网络,计算出智能节点之间的最短路径后将结果代入针对其层次延迟性而设计的分配算法AAoRN(Allocation Algorithm of Rete Inference Nodes),从而将推理节点最优分配至各个智能节点.理论分析和实验结果表明,本文机制在有效利用智能节点资源的同时降低了大致55%的延迟.展开更多
基金Project(50474033)supported by the National Natural Science Foundation of China
文摘To find out all dependency relationships in which metaphors probably exist between syntax constituents in a given sentence,a dependency tree matching algorithm oriented to Chinese metaphor processing is proposed based on a research of unordered tree inclusion matching.In this algorithm,the pattern library is composed of formalization dependency syntax trees that are derived from large-scale metaphor sentences.These kinds of metaphor sentences are saved in the pattern library in advance.The main process of this algorithm is up-down searching and bottom-up backtracking revising.The algorithm discovers potential metaphoric structures in Chinese sentences from metaphoric dependency pattern library.Finally,the feasibility and efficiency of the new matching algorithm are further testified by the results of a series of experiments on dependency pattern library.Hence,accurate dependency relationships can be achieved through this algorithm.
文摘智能环境传统的规则推理机制中,网关内布置的推理机从各种传感器中获取推理所需数据并与规则库相匹配,承担整个推理工作.本文利用Rete算法将规则构建为推理网络,并结合雾计算的概念将Rete推理节点分配至环境内配置的智能节点中协同推理以减轻网关负载,由此推理节点的分配成为关键,分配不合理将导致资源利用不平衡及响应延迟.本文利用活动影响下规则触发的规律设计了活动聚类算法CoA(Clustering of Activities)对活动聚类后分别建立其推理网络,计算出智能节点之间的最短路径后将结果代入针对其层次延迟性而设计的分配算法AAoRN(Allocation Algorithm of Rete Inference Nodes),从而将推理节点最优分配至各个智能节点.理论分析和实验结果表明,本文机制在有效利用智能节点资源的同时降低了大致55%的延迟.