接诉即办是实现社会治理智能化、提高人民满意度的重要举措,其中精准分析民众诉求智能匹配工单处理部门,实现诉求的快速响应、高效办理尤为关键;然而,民众诉求数据中的诉求描述不清晰、类别混淆且比例失衡会导致诉求类别分析困难,影响...接诉即办是实现社会治理智能化、提高人民满意度的重要举措,其中精准分析民众诉求智能匹配工单处理部门,实现诉求的快速响应、高效办理尤为关键;然而,民众诉求数据中的诉求描述不清晰、类别混淆且比例失衡会导致诉求类别分析困难,影响了智能派单的效率与准确性。针对上述问题,提出编解码器结构的诉求层次多标签分类模型(HMCHotline)。首先,在文本编码器中引入诉求领域中的细粒度关键词先验知识以抑制噪声干扰,并融合诉求的时空信息提高语义特征的判别力;其次,利用标签层次结构生成具有层次与语义感知的标签嵌入,并构建基于Transformer模型的标签解码器,利用诉求的语义特征和标签嵌入进行标签解码;同时,在标签的层级依赖关系基础上引入动态标签表策略限制标签的解码范围,以解决标签不一致问题;最后,采用Softmax分组策略将样本数量相近的标签类别分为同组进行Softmax操作,从而缓解由标签长尾分布导致的分类准确率低的问题。在Hotline、RCV1(Reuters Corpus VolumeⅠ)-v2和WOS(Web Of Science)数据集上的实验结果表明,相较于层次感知的标签语义匹配网络(HiMatch),所提模型的Micro-F1分别提高了1.65、2.06和0.43个百分点,验证了模型的有效性。展开更多
Building up graph models to simulate scale-free networks is an important method since graphs have been used in researching scale-free networks. One use labelled graphs for distinguishing objects of communication and i...Building up graph models to simulate scale-free networks is an important method since graphs have been used in researching scale-free networks. One use labelled graphs for distinguishing objects of communication and information networks. In this paper some methods are given for constructing larger felicitous graphs from smaller graphs having special felicitous labellings, and some network models are shown to be felicitous.展开更多
XML data can be represented by a tree or graph and the query processing for XML data requires the structural information among nodes. Designing an efficient labeling scheme for the nodes of Order-Sensitive XML trees i...XML data can be represented by a tree or graph and the query processing for XML data requires the structural information among nodes. Designing an efficient labeling scheme for the nodes of Order-Sensitive XML trees is one of the important methods to obtain the excellent management of XML data. Previous labeling schemes such as region and prefix often sacrifice updating performance and suffer increasing labeling space when inserting new nodes. To overcome these limitations, in this paper we propose a new labeling idea of separating structure from order. According to the proposed idea, a novel Prime-based Middle Fraction Labeling Scheme(PMFLS) is designed accordingly, in which a series of algorithms are proposed to obtain the structural relationships among nodes and to support updates. PMFLS combines the advantages of both prefix and region schemes in which the structural information and sequential information are separately expressed. PMFLS also supports Order-Sensitive updates without relabeling or recalculation, and its labeling space is stable. Experiments and analysis on several benchmarks are conducted and the results show that PMFLS is efficient in handling updates and also significantly improves the performance of the query processing with good scalability.展开更多
The design of large disk array architectures leads to interesting combinatorial problems. Minimizing the number of disk operations when writing to consecutive disks leads to the concept of “cluttered orderings” whic...The design of large disk array architectures leads to interesting combinatorial problems. Minimizing the number of disk operations when writing to consecutive disks leads to the concept of “cluttered orderings” which were introduced for the complete graph by Cohen et al. (2001). Mueller et al. (2005) adapted the concept of wrapped Δ-labellings to the complete bipartite case. In this paper, we give some sequence in order to generate wrapped Δ-labellings as cluttered orderings for the complete bipartite graph. New sequence we give is different from the sequences Mueller et al. gave, though the same graphs in which these sequences are labeled.展开更多
文摘接诉即办是实现社会治理智能化、提高人民满意度的重要举措,其中精准分析民众诉求智能匹配工单处理部门,实现诉求的快速响应、高效办理尤为关键;然而,民众诉求数据中的诉求描述不清晰、类别混淆且比例失衡会导致诉求类别分析困难,影响了智能派单的效率与准确性。针对上述问题,提出编解码器结构的诉求层次多标签分类模型(HMCHotline)。首先,在文本编码器中引入诉求领域中的细粒度关键词先验知识以抑制噪声干扰,并融合诉求的时空信息提高语义特征的判别力;其次,利用标签层次结构生成具有层次与语义感知的标签嵌入,并构建基于Transformer模型的标签解码器,利用诉求的语义特征和标签嵌入进行标签解码;同时,在标签的层级依赖关系基础上引入动态标签表策略限制标签的解码范围,以解决标签不一致问题;最后,采用Softmax分组策略将样本数量相近的标签类别分为同组进行Softmax操作,从而缓解由标签长尾分布导致的分类准确率低的问题。在Hotline、RCV1(Reuters Corpus VolumeⅠ)-v2和WOS(Web Of Science)数据集上的实验结果表明,相较于层次感知的标签语义匹配网络(HiMatch),所提模型的Micro-F1分别提高了1.65、2.06和0.43个百分点,验证了模型的有效性。
文摘Building up graph models to simulate scale-free networks is an important method since graphs have been used in researching scale-free networks. One use labelled graphs for distinguishing objects of communication and information networks. In this paper some methods are given for constructing larger felicitous graphs from smaller graphs having special felicitous labellings, and some network models are shown to be felicitous.
基金supported by the National Science Foundation of China(Grant No.61272067,61370229)the National Key Technology R&D Program of China(Grant No.2012BAH27F05,2013BAH72B01)+1 种基金the National High Technology R&D Program of China(Grant No.2013AA01A212)the S&T Projects of Guangdong Province(Grant No.2016B010109008,2014B010117007,2015A030401087,2015B010109003,2015B010110002)
文摘XML data can be represented by a tree or graph and the query processing for XML data requires the structural information among nodes. Designing an efficient labeling scheme for the nodes of Order-Sensitive XML trees is one of the important methods to obtain the excellent management of XML data. Previous labeling schemes such as region and prefix often sacrifice updating performance and suffer increasing labeling space when inserting new nodes. To overcome these limitations, in this paper we propose a new labeling idea of separating structure from order. According to the proposed idea, a novel Prime-based Middle Fraction Labeling Scheme(PMFLS) is designed accordingly, in which a series of algorithms are proposed to obtain the structural relationships among nodes and to support updates. PMFLS combines the advantages of both prefix and region schemes in which the structural information and sequential information are separately expressed. PMFLS also supports Order-Sensitive updates without relabeling or recalculation, and its labeling space is stable. Experiments and analysis on several benchmarks are conducted and the results show that PMFLS is efficient in handling updates and also significantly improves the performance of the query processing with good scalability.
文摘The design of large disk array architectures leads to interesting combinatorial problems. Minimizing the number of disk operations when writing to consecutive disks leads to the concept of “cluttered orderings” which were introduced for the complete graph by Cohen et al. (2001). Mueller et al. (2005) adapted the concept of wrapped Δ-labellings to the complete bipartite case. In this paper, we give some sequence in order to generate wrapped Δ-labellings as cluttered orderings for the complete bipartite graph. New sequence we give is different from the sequences Mueller et al. gave, though the same graphs in which these sequences are labeled.
