Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method,Evaluation, and Application

In this paper, we study the problem of extracting variable-depth "logical document hierarchy" from long documents, namely organizing the recognized "physical document objects" into hierarchical structures. The discovery of logical document hierarchy is the vital step to support many downstream applications (e.g., passage-based retrieval and high-quality information extraction). However, long documents, containing hundreds or even thousands of pages and a variable-depth hierarchy, challenge the existing methods. To address these challenges, we develop a framework, namely Hierarchy Extraction from Long Document (HELD), where we "sequentially" insert each physical object at the proper position on the current tree. Determining whether each possible position is proper or not can be formulated as a binary classification problem. To further improve its effectiveness and efficiency, we study the design variants in HELD, including traversal orders of the insertion positions, heading extraction explicitly or implicitly, tolerance to insertion errors in predecessor steps, and so on. As for evaluations, we find that previous studies ignore the error that the depth of a node is correct while its path to the root is wrong. Since such mistakes may worsen the downstream applications seriously, a new measure is developed for a more careful evaluation. The empirical experiments based on thousands of long documents from Chinese financial market, English financial market and English scientific publication show that the HELD model with the "root-to-leaf" traversal order and explicit heading extraction is the best choice to achieve the tradeoff between effectiveness and efficiency with the accuracy of 0.972,6, 0.729,1 and 0.957,8 in the Chinese financial, English financial and arXiv datasets, respectively. Finally, we show that the logical document hierarchy can be employed to significantly improve the performance of the downstream passage retrieval task. In summary, we conduct a systematic study on this task in terms of methods, evaluations, and applications.     

轮胎花纹图像检索技术综述

轮胎花纹图像检索在交通事故处理及刑事案件侦破中是获取破案信息的重要手段,虽然基于内容的图像检索技术已发展数十年,但由于轮胎花纹图像数据的来源及应用场景特殊等因素,目前这方面的研究文献并不多。在研究近年来轮胎花纹图像检索领域相关文献的基础上,对该领域的技术现状进行总结分析。首先,围绕轮胎花纹纹理特征提取和高层语义特征提取两项关键技术描述了该领域的主要研究成果,并总结了轮胎花纹数据库以及检索性能评价指标。然后,分别针对轮胎花纹低层特征和高层特征提取进行实验对比并分析结果。最后,结合现有技术及实际应用需求,分析了该领域的技术发展趋势并指出了未来的研究方向。     

基于渲染图像角度结构特征的三维模型检索方法

为了充分利用三维模型的颜色、形状、纹理等特征,提出以三维模型渲染图像为数据集,利用渲染图像角度结构特征实现三维模型检索。首先,该方法以三维模型渲染图像为测试集,利用已有类别标记的自然图像作为训练集,通过骨架形状上下文特征对渲染图像进行分类,提取角度结构特征,建立特征库;然后,对输入的自然图像提取角度结构特征,与特征库中的角度结构特征进行相似度匹配计算,实现三维模型检索。实验结果表明, 充分利用 渲染图像的颜色、形状和空间信息是实现三维模型检索的有效方法。     

基于多属性效用匹配的应急案例检索方法研究*

案例推理是一种依靠历史案例经验来指导人们认识和解决问题的方法,比较适用于信息缺失却需要快速反应的应急决策领域。鉴于非常规突发事件与常规突发事件存在诸多差异,在应急案例库中很难检索到与当前所发生的非常规事件相似的案例,从而可能导致应急案例检索系统失效。为了解决这一难题,首先把非常规突发事件按照时间序列划分成若干阶段,对每一阶段的特定子事件即常规突发事件进行匹配与检索。随后以证据理论为主要工具,构建基于多属性效用匹配的应急案例检索模型并求解算法,为应急决策提供技术支持。最后的实例分析验证了所建模型的有效性和可行性。     

一种新型隐私数据库秘密同态检索协议

针对隐私数据查询中的隐私泄露威胁模型,本文提出了一种新型隐私数据库秘密同态检索协议,该协议基于SomeWhat部分同态算法进行设计,通过使用密文同态运算性质较好的解决了该威胁模型中涉及到的隐私泄露问题,同时本文在证明该协议正确性和安全性的基础上,通过适当的参数选择,对该协议的同态算法进行了测试,给出了算法的运行效率。     

云环境下一种隐私文件分类存储与保护方案*

针对云计算环境下存储的隐私文件会造成隐私泄漏、信息量过载,使用传统加密算法对隐私文件进行加密后再外包给云的方法严重影响了隐私文件的可检索性问题进行研究,提出了一种既能够有效减少云环境中信息存储量过载,同时又能够满足隐私文件的加密保护和检索的方案。该方案首先对隐私文件进行分类,将直接隐私文件存储在数据拥有者本地存储器,非直接隐私文件则加密后上传云环境中存储,实现了隐私文件的分类存储和安全保护。然后基于改进的哈希列表建立了一个包含文件属性描述的文件检索索引、生成了文件检索陷门,实现了使用关键词在密文状态下完成文件检索。最后,通过详细的理论分析和实验对比分析证明了方案的可行性和实用性。     

支持用户撤销的可验证密文检索方案

为解决恶意云服务器可能发送错误或者伪造的查询结果给用户,且授权用户可能在检索完成之后将密钥信息私自发送给非授权用户的问题,构造了一种支持用户撤销的可验证密文检索方案。首先,利用加密算法对用户文档加密、对关键词签名;其次,运用搜索算法对需要检索的文档进行检索;最后,运用验证算法和用户撤销算法对检索结果进行验证,以及对未检索文档进行再一次加密保护。分析结果表明,所提方案能够在保证数据完整性的前提下完成精确检索,且通过重加密机制实现了用户撤销,保证了系统的安全性,该方案满足不可区分性选择关键词攻击（IND-CKA）安全。     

Analyzing Residue Surface Proximity to Interpret Molecular Dynamics

The surface of a molecule holds important information about the interaction behavior with other molecules. In dynamic folding or docking processes, residues of amino acids with different properties change their position within the molecule over time. The atoms of the residues that are accessible to the solvent can directly contribute to binding interactions, while residues buried within the molecular structure contribute to the stability of the molecule. Understanding patterns and causality of structural changes is important for experts in the pharmaceutical domain, e.g., in the process of drug design. We apply an iterative computation of the Solvent Accessible Surface in order to extract virtual layers of a molecule. The extraction allows to track the movement of residues in the body of the molecule, with respect to the distance of the residue to the surface or the core during dynamics simulations. We visualize the obtained layer information for the complete time span of the molecular dynamics simulation as a 2D‐map and for individual time‐steps as a 3D‐representation of the molecule. The data acquisition has been implemented alongside with further analysis functionality in a prototypical application, which is available to the public domain. We underline the feasibility of our approach with a study from the pharmaceutical domain, where our approach has been used for novel insights into the folding behavior of μ‐conotoxins.     

An improved Urdu stemming algorithm for text mining based on multi-step hybrid approach

Stemming is the basic operation in Natural language processing (NLP) to remove derivational and inflectional affixes without performing a morphological analysis. This practice is essential to extract the root or stem. In NLP domains, the stemmer is used to improve the process of information retrieval (IR), text classifications (TC), text mining (TM) and related applications. In particular, Urdu stemmers utilize only uni-gram words from the input text by ignoring bigrams, trigrams, and n-gram words. To improve the process and efficiency of stemming, bigrams and trigram words must be included. Despite this fact, there are a few developed methods for Urdu stemmers in the past studies. Therefore, in this paper, we proposed an improved Urdu stemmer, using hybrid approach divided into multi-step operation, to deal with unigram, bigram, and trigram features as well. To evaluate the proposed Urdu stemming method, we have used two corpora; word corpus and text corpus. Moreover, two different evaluation metrics have been applied to measure the performance of the proposed algorithm. The proposed algorithm achieved an accuracy of 92.97% and compression rate of 55%. These experimental results indicate that the proposed system can be used to increase the effectiveness and efficiency of the Urdu stemmer for better information retrieval and text mining applications.     

融合颜色词袋特征的视觉词汇树图像检索

针对由图像灰度空间产生的传统词袋模型SIFT特征无法体现图像的颜色信息的问题,提出了一种融合颜色特征的视觉词汇树来对图像进行描述。提取SIFT特征并建立词汇树,获取图像的SIFT表示向量。利用K-means方法对图像库中的所有图像的HSV值进行聚类,获得基于HSV空间的颜色词袋表示向量,避免了传统颜色直方图方法所带来的量化误差。将SIFT特征与颜色词袋特征进行融合,完成了图像的全局特征和局部特征的融合。然后,计算融合特征的相似度,将相似度从高到低排序,完成图像检索。为了验证本方法的有效性,选择Corel图像库对算法性能进行实验分析,从主观评价和客观评价标准分别进行评价,并与传统方法进行了对比。结果表明,特征融合的检索性能与单一特征方法相比有较大提高。特征融合方法的平均检索查准率和查全率-查准率等评价指标,对比传统方法均有不同程度提高。