An approach to domain-based scalable context management architecture in pervasive environments

In pervasive environments, context management systems are expected to administrate large volume of contextual information that is captured from spatial to nonspatial elements. Research in context-aware computing produced a number of middleware systems for context management to intermediate the communications between applications and context providers. In particular, in pervasive environments, the design of distributed storage, retrieval and propagation mechanisms of context information across domains is vital. In this paper, we propose a domain-based approach to address the requirements of scalable distributed context management, cross-domain efficient context information dissemination and domain-based privacy policy enforcement. We propose infinitum, a middleware architecture that incorporates the management and communication benefits of the Google Wave Federation Protocol, while also taking advantage of the semantic and inference benefits of ontology-based context models. This architecture establishes a robust cross-domain scalable context management and collaboration framework, which has been implemented and evaluated in a real-life application of “SMART University” to support virtual team collaboration.     

Search structures and algorithms for personalized ranking

As data of an unprecedented scale are becoming accessible on the Web, personalization, of narrowing down the retrieval to meet the user-specific information needs, is becoming more and more critical. For instance, while web search engines traditionally retrieve the same results for all users, they began to offer beta services to personalize the results to adapt to user-specific contexts such as prior search history or other application contexts. In a clear contrast to search engines dealing with unstructured text data, this paper studies how to enable such personalization in the context of structured data retrieval. In particular, we adopt contextual ranking model to formalize personalization as a cost-based optimization over collected contextual rankings. With this formalism, personalization can be abstracted as a cost-optimal retrieval of contextual ranking, closely matching user-specific retrieval context. With the retrieved matching context, we adopt a machine learning approach, to effectively and efficiently identify the ideal personalized ranked results for this specific user. Our empirical evaluations over synthetic and real-life data validate both the efficiency and effectiveness of our framework.     

An evaluative baseline for geo-semantic relatedness and similarity

In geographic information science and semantics, the computation of semantic similarity is widely recognised as key to supporting a vast number of tasks in information integration and retrieval. By contrast, the role of geo-semantic relatedness has been largely ignored. In natural language processing, semantic relatedness is often confused with the more specific semantic similarity. In this article, we discuss a notion of geo-semantic relatedness based on Lehrer’s semantic fields, and we compare it with geo-semantic similarity. We then describe and validate the Geo Relatedness and Similarity Dataset (GeReSiD), a new open dataset designed to evaluate computational measures of geo-semantic relatedness and similarity. This dataset is larger than existing datasets of this kind, and includes 97 geographic terms combined into 50 term pairs rated by 203 human subjects. GeReSiD is available online and can be used as an evaluation baseline to determine empirically to what degree a given computational model approximates geo-semantic relatedness and similarity.     

Extracting semantic knowledge from web context for multimedia IR: a taxonomy,survey and challenges

Since its invention, the Web has evolved into the largest multimedia repository that has ever existed. This evolution is a direct result of the explosion of user-generated content, explained by the wide adoption of social network platforms. The vast amount of multimedia content requires effective management and retrieval techniques. Nevertheless, Web multimedia retrieval is a complex task because users commonly express their information needs in semantic terms, but expect multimedia content in return. This dissociation between semantics and content of multimedia is known as the semantic gap. To solve this, researchers are looking beyond content-based or text-based approaches, integrating novel data sources. New data sources can consist of any type of data extracted from the context of multimedia documents, defined as the data that is not part of the raw content of a multimedia file. The Web is an extraordinary source of context data, which can be found in explicit or implicit relation to multimedia objects, such as surrounding text, tags, hyperlinks, and even in relevance-feedback. Recent advances in Web multimedia retrieval have shown that context data has great potential to bridge the semantic gap. In this article, we present the first comprehensive survey of context-based approaches for multimedia information retrieval on the Web. We introduce a data-driven taxonomy, which we then use in our literature review of the most emblematic and important approaches that use context-based data. In addition, we identify important challenges and opportunities, which had not been previously addressed in this area.

     

基于上下文的概念语义相似度计算模型

针对概念语义相似度计算方法在信息检索中存在的漏检、误检等问题,提出一种基于上下文的计算本体内概念间语义相似度的模型。该模型分别从概念的父节点、子节点以及概念间路径权重3个角度进行计算,加权求和并求得语义相似度。实验结果表明,该模型的计算结果更加接近专家的经验值,为概念之间的语义关系提供了有效的量化。     

Supervised Coarse-to-Fine Semantic Hashing for cross-media retrieval

Due to its storage efficiency and fast query speed, cross-media hashing methods have attracted much attention for retrieving semantically similar data over heterogeneous datasets. Supervised hashing methods, which utilize the labeled information to promote the quality of hashing functions, achieve promising performance. However, the existing supervised methods generally focus on utilizing coarse semantic information between samples (e.g. similar or dissimilar), and ignore fine semantic information between samples which may degrade the quality of hashing functions. Accordingly, in this paper, we propose a supervised hashing method for cross-media retrieval which utilizes the coarse-to-fine semantic similarity to learn a sharing space. The inter-category and intra-category semantic similarity are effectively preserved in the sharing space. Then an iterative descent scheme is proposed to achieve an optimal relaxed solution, and hashing codes can be generated by quantizing the relaxed solution. At last, to further improve the discrimination of hashing codes, an orthogonal rotation matrix is learned by minimizing the quantization loss while preserving the optimality of the relaxed solution. Extensive experiments on widely used Wiki and NUS-WIDE datasets demonstrate that the proposed method outperforms the existing methods.     

Hierarchy as a new data type for qualitative variables

The concept of hierarchy has being explored by the computer science communities during last few decades. Relatively simple hierarchical structures found extensive use in such diverse areas as data modeling, information retrieval, knowledge representation and processing, natural language, pattern recognition, and so on. Recent investigations in information retrieval and data integration have emphasized the use of ontologies and semantic similarity functions as a mechanism for comparing objects that can be retrieved or integrated across heterogeneous repositories. Hierarchies being a simpler, albeit very useful, version of ontologies, can perfectly contribute to model solutions of these problems. Present paper aims to illustrate above thesis by discussing a simple method of information retrieval that uses a hierarchical qualitative data organization. Its main goal is to retrieve objects from any database that are just close to a desired item and control the retrieval process up to a given error, called herein confusion. For doing this, we define a semantic dissimilarity (confusion) between objects to be retrieved as well as introduce a calculus of predicates based on the confusion function.     

Semantic consistent adversarial cross-modal retrieval exploiting semantic similarity

Cross-modal retrieval aims to search the semantically similar instances from the other modalities given a query from one modality. However, the differences of the distributions and representations between different modalities make that the similarity of different modalities can not be measured directly. To address this problem, in this paper, we propose a novel semantic consistent adversarial cross-modal retrieval (SC-ACMR), which learns semantic consistent representation for different modalities under adversarial learning framework by considering the semantic similarity from intra-modality and inter-modality. Specifically, for intra-modality, we minimize the intra-class distances. For the inter-modality, we require class center of different modalities with same semantic label to be as close as possible, and also minimize the distances between the samples and the class center with same semantic label from different modalities. Furthermore, we preserve the semantic similarity of transformed features of different modalities through a semantic similarity matrix. Comprehensive experiments on two benchmark datasets are conducted and the experimental results show that the proposed method have learned more compact semantic representations and achieved better performance than many existing methods in cross-modal retrieval.

     

A semantic approach to concept lattice-based information retrieval

The volume of available information is growing, especially on the web, and in parallel the questions of the users are changing and becoming harder to satisfy. Thus there is a need for organizing the available information in a meaningful way in order to guide and improve document indexing for information retrieval applications taking into account more complex data such as semantic relations. In this paper we show that Formal Concept Analysis (FCA) and concept lattices provide a suitable and powerful support for such a task. Accordingly, we use FCA to compute a concept lattice, which is considered both a semantic index to organize documents and a search space to model terms. We introduce the notions of cousin concepts and classification-based reasoning for navigating the concept lattice and retrieve relevant information based on the content of concepts. Finally, we detail a real-world experiment and show that the present approach has very good capabilities for semantic indexing and document retrieval.     

深度多模态融合服装风格检索

目的 服装检索方法是计算机视觉与自然语言处理领域的研究热点,其包含基于内容与基于文本的两种查询模态。然而传统检索方法通常存在检索效率低的问题,且很少研究关注服装在风格上的相似性。为解决这些问题,本文提出深度多模态融合的服装风格检索方法。方法 提出分层深度哈希检索模型,基于预训练的残差网络ResNet（residual network）进行迁移学习,并把分类层改造成哈希编码层,利用哈希特征进行粗检索,再用图像深层特征进行细检索。设计文本分类语义检索模型,基于LSTM（long short-term memory）设计文本分类网络以提前分类缩小检索范围,再以基于doc2vec提取的文本嵌入语义特征进行检索。同时提出相似风格上下文检索模型,其参考单词相似性来衡量服装风格相似性。最后采用概率驱动的方法量化风格相似性,并以最大化该相似性的结果融合方法作为本文检索方法的最终反馈。结果 在Polyvore数据集上,与原始ResNet模型相比,分层深度哈希检索模型的top5平均检索精度提高11.6%,检索速度提高2.57 s/次。与传统文本分类嵌入模型相比,本文分类语义检索模型的top5查准率提高29.96%,检索速度提高16.53 s/次。结论 提出的深度多模态融合的服装风格检索方法获得检索精度与检索速度的提升,同时进行了相似风格服装的检索使结果更具有多样性。     

基于大规模语料库的汉语词义相似度计算方法

词义相似度的计算是自然语言处理领域的关键问题之一,它在信息检索中的查询扩展、机器翻译中的模块识别,以及句法分析、词义消歧等任务中都发挥着重要的作用。该文研究了基于大规模语料库的汉语词义相似度计算方法,系统地比较分析了上下文特征权值的选择、向量相似度计算方法、基于窗口和基于依存关系的表征形式、新闻语体和网络语体的差异。实验结果表明,在网络语言语料上,基于窗口选取上下文特征,用互信息PMI来计算权值,采用cosine来计算相似度,取得了最好的词义相似度结果。     

语义视频检索的现状和研究进展

概述了图像的可视化特征如颜色、纹理、形状和运动信息,时空关系分析,以及多特征目标提取和相似度量度;分析了视频语义的提取,语义查询、检索;探讨了视频语义检索的性能评估,存在的问题和发展方向。     

Content based similarity of geographic classes organized as partition hierarchies

In this paper we propose a method to measure the semantic similarity of geographic classes organized as partition hierarchies within Naive Geography. The contribution of this work consists in extending and integrating the information content approach, and the method for comparing concept attributes in the ontology management system SymOntos developed at IASI. As a result, this proposal allows us to address both the concept similarity within the partition hierarchy, and the attribute similarity of geographic classes and, therefore, to reduce the gap among the different similarity approaches defined in the literature.

图像数据的结构化协同标注与检索

通过分析图像数据对语义信息的检索需求,提出一种表达图像信息的结构化方法,并定义一种根据图像中隐含语义信息来判定相似度的算法。该方法在一定程度上克服了基于内容的图像检索和基于文本的元数据图像检索这2种常用图像检索方法缺乏语义信息匹配上的不足。原型系统根据结构化协同标注中语义信息的丰富程度与图像检索的精确程度,证明了该方法的有效性。     

Multimodal Retrieval using Mutual Information based Textual Query Reformulation

Multimodal Retrieval is a well-established approach for image retrieval. Usually, images are accompanied by text caption along with associated documents describing the image. Textual query expansion as a form of enhancing image retrieval is a relatively less explored area. In this paper, we first study the effect of expanding textual query on both image and its associated text retrieval. Our study reveals that judicious expansion of textual query through keyphrase extraction can lead to better results, either in terms of text-retrieval or both image and text-retrieval. To establish this, we use two well-known keyphrase extraction techniques based on tf-idf and KEA. While query expansion results in increased retrieval efficiency, it is imperative that the expansion be semantically justified. So, we propose a graph-based keyphrase extraction model that captures the relatedness between words in terms of both mutual information and relevance feedback. Most of the existing works have stressed on bridging the semantic gap by using textual and visual features, either in combination or individually. The way these text and image features are combined determines the efficacy of any retrieval. For this purpose, we adopt Fisher-LDA to adjudge the appropriate weights for each modality. This provides us with an intelligent decision-making process favoring the feature set to be infused into the final query. Our proposed algorithm is shown to supersede the previously mentioned keyphrase extraction algorithms for query expansion significantly. A rigorous set of experiments performed on ImageCLEF-2011 Wikipedia Retrieval task dataset validates our claim that capturing the semantic relation between words through Mutual Information followed by expansion of a textual query using relevance feedback can simultaneously enhance both text and image retrieval.     

Building semantic trees from XML documents

The distributed nature of the Web, as a decentralized system exchanging information between heterogeneous sources, has underlined the need to manage interoperability, i.e., the ability to automatically interpret information in Web documents exchanged between different sources, necessary for efficient information management and search applications. In this context, XML was introduced as a data representation standard that simplifies the tasks of interoperation and integration among heterogeneous data sources, allowing to represent data in (semi-) structured documents consisting of hierarchically nested elements and atomic attributes. However, while XML was shown most effective in exchanging data, i.e., in syntactic interoperability, it has been proven limited when it comes to handling semantics, i.e.,  semantic interoperability, since it only specifies the syntactic and structural properties of the data without any further semantic meaning. As a result, XML semantic-aware processing has become a motivating challenge in Web data management, requiring dedicated semantic analysis and disambiguation methods to assign well-defined meaning to XML elements and attributes. In this context, most existing approaches: (i) ignore the problem of identifying ambiguous XML elements/nodes, (ii) only partially consider their structural relationships/context, (iii) use syntactic information in processing XML data regardless of the semantics involved, and (iv) are static in adopting fixed disambiguation constraints thus limiting user involvement. In this paper, we provide a new XML Semantic Disambiguation Framework titled XSDFdesigned to address each of the above limitations, taking as input: an XML document, and then producing as output a semantically augmented XML tree made of unambiguous semantic concepts extracted from a reference machine-readable semantic network. XSDF consists of four main modules for: (i) linguistic pre-processing of simple/compound XML node labels and values, (ii) selecting ambiguous XML nodes as targets for disambiguation, (iii) representing target nodes as special sphere neighborhood vectors including all XML structural relationships within a (user-chosen) range, and (iv) running context vectors through a hybrid disambiguation process, combining two approaches: concept-basedand context-based disambiguation, allowing the user to tune disambiguation parameters following her needs. Conducted experiments demonstrate the effectiveness and efficiency of our approach in comparison with alternative methods. We also discuss some practical applications of our method, ranging over semantic-aware query rewriting, semantic document clustering and classification, Mobile and Web services search and discovery, as well as blog analysis and event detection in social networks and tweets.