FODA — the formal specification of ODA document structures and its use as a basis for conformance testing

The Office Document Architecture (ODA) is an International Standard which is developed by TC 97/sc 18 of the International Organization for Standardization (ISO) in close collaboration with CCITT's Study Group VIII and with ECMA. This paper describes the current state of a formal specification of the ODA document structures by mathematical means and its use for conformance specification and conformance testing.     

汉语语音文档检索中后验概率的索引方法

基于音节Lattice形式的语音识别结果来实现汉语语音文档检索,不但可以成功规避词表外词问题,而且Lattice这种多候选形式也能有效补偿识别错误对检索性能的影响.在基于音节Lattice的汉语语音文档检索研究中,针对已有索引方法的不足,提出了一种基于后验概率的索引方法,对向量空间模型进行改进,以音节和K步邻接音节对作为索引项,以它们在语音文档中的后验概率值作为索引项权重.检索实验表明,文中的方法更适用于基于音节Lattice的语音文档检索任务,各项改进都达到了预期效果.     

基于Word文档的数据隐藏方法

在分析当前数据隐藏与恢复相关技术研究基础上,参照微软官方最新公布的复合文档存储规范,从利用载体Word文档现有空间中未真正使用部分和适度扩展新空间两条思路出发,设计一种利用Word文档作载体隐藏秘密信息的解决方案,包括在文字、各种嵌入式对象及其相应控制结构数据中隐藏信息。实践表明,隐藏数据后的载体文档可以被正常拷贝和使用电子邮件传送,根据需要隐藏的信息随机选择使用该方案,被隐藏信息更不容易被侦测出来,被二次编辑后被隐藏信息一般不会被破坏,鲁棒性不错,具有一定的实用价值。     

EDITORIAL

The process undertaken by an information seeker, in order to form relevance decisions regarding documents, is defined as “Document Triage.” To better facilitate users’ needs in their triage activities, interactive interfaces have begun to evolve within on-line academic repositories. In order to complement current work on interface design and interaction, and produce custom guidelines to inform the creation of triage interfaces, we examine how interfaces that alter the document presentation and structure affect information seekers’ visual and navigational attention. We present a set of heuristics for both creating and evaluating such interfaces.     

将Access数据库中图文信息导出到Word文档的方法

该文介绍了将Access数据库中的图文混编内容导出到Word文档的方法,并给出了用Visual Basic 6.0实现的程序实例。     

Active XML文档安全重写判定算法

研究了AXML文档安全重写判定问题,即判定给定AXML文档通过触发其包含的服务调用生成的文档集合是否能够全部重写为符合目标模式的文档实例.基于树自动机理论,定义了用于抽象AXML文档的树自动机--ATA机(AXML treeautomata),ATA机等价于给定AXML文档通过触发其包含的服务调用所能生成的文档集合.基于ATA机,提出一个AXML文档安全重写判定算法,表明了该算法的正确性及有效性.     

Parallelization of a dynamic SVD clustering algorithm and its application in information retrieval

We describe an implementation of a parallel document clustering scheme based on latent semantic indexing, which uses singular value decomposition. Given a set of documents, the clustering algorithm is dynamic in the sense that it automatically infers the number of clusters to be output. The parallel version has been implemented on a LAN and on a dual‐core system. Experimental evaluation of the algorithm shows an average speed‐up of 6.22 for the LAN implementation and an average speed‐up of 3.71 for the dual‐core implementation, while still maintaining a precision and recall in the range [0.85, 1]. To put these implementations in the context of information retrieval, we use the parallel clustering algorithm and develop a document similarity search system. The similarity search system shows good performance in terms of precision and recall. Copyright © 2010 John Wiley & Sons, Ltd.     

基于流形学习和SVM的Web文档分类算法

为解决Web文档分类问题,提出一种基于流形学习和SVM的Web文档分类算法。该算法利用流形学习算法LPP对训练集中的高维Web文档空间进行非线性降维,从中找出隐藏在高维观测数据中有意义的低维结构,在降维后的低维特征空间中利用乘性更新规则的优化SVM进行分类预测。实验结果表明该算法以较少的运行时间获得更高的分类准确率。     

基于特征的文档图像检索

提出一种综合利用文档图像的段落特征和局部像素分布相对差特征进行文档图像检索的方法。给出段落特征和局部像素分布相对差特征的定义、提取方法以及基于这2个特征结合使用的检索方法。段落特征这一全局特征以及局部像素分布相对差特征这一局部特征相结合能够较好地表征和区分文档图像,检索方法将两者充分结合取得较好的效果。