The typical RDF querying method is a structured query language such as SPARQL. However, a structured query language requires issuers to understand the data model and query language syntax, limiting the accessibility of RDF data. The keyword query is regarded as an intuitive way for searching the RDF data. This paper proposes a keyword query approach based on the community structure of the RDF entity graph, which utilizes the characteristics of the community structure on the RDF graph. We propose a novel RDF entity graph model by designing an efficient entity index mechanism by treating the RDF entity as the virtual document, which reduces the graph scale while improving the efficiency of retrieving entities. We design an effective hierarchical and overlapping community-based index mechanism on the RDF entity graph, improving the efficiency and accuracy of the subgraph (sub-community) matching. Our approach takes full advantage of the schema of the RDF data and the community structural characteristic of the RDF entity graph. We evaluate our approach using two real-world datasets, and the experiment demonstrates the effectiveness and efficiency of our approach.

Discovering hyponym relations among domain-specific terms is a fundamental task in taxonomy learning and knowledge acquisition. However, the great diversity of various domain corpora and the lack of labeled training sets make this task very challenging for conventional methods that are based on text content. The hyperlink structure of Wikipedia article pages was found to contain recurring network motifs in this study, indicating the probability of a hyperlink being a hyponym hyperlink. Hence, a novel hyponym relation extraction approach based on the network motifs of Wikipedia hyperlinks was proposed. This approach automatically constructs motif-based features from the hyperlink structure of a domain; every hyperlink is mapped to a 13-dimensional feature vector based on the 13 types of three-node motifs. The approach extracts structural information from Wikipedia and heuristically creates a labeled training set. Classification models were determined from the training sets for hyponym relation extraction. Two experiments were conducted to validate our approach based on seven domain-specific datasets obtained from Wikipedia. The first experiment, which utilized manually labeled data, verified the effectiveness of the motif-based features. The second experiment, which utilized an automatically labeled training set of different domains, showed that the proposed approach performs better than the approach based on lexico-syntactic patterns and achieves comparable result to the approach based on textual features. Experimental results show the practicability and fairly good domain scalability of the proposed approach.

Speculative multithreading (SpMT) is a thread level automatic parallelization technique to accelerate sequential programs. Since approaches based on heuristic rules only get the local optimal speculative thread solution and have reached their speedup performance limit, machine learning approaches have been introduced into speculative multithreading to avoid the shortcomings of the heuristic rules relied on experience. However, few irregular programs can meet the need for training model of machine learning. To solve this problem, we first build feature sets based on Olden benchmarks and then disturb them into new sets. With the new sets, virtual samples are generated by abstract syntax trees (ASTs). By this means, we effectively resolve the shortage of samples for speculative multithreading based on machine learning. On Prophet, which is a generic SpMT processor to evaluate the performance of multithread programs, the validity of virtual samples is verified and reaches an average speedup of 1.47. Experiments show that the virtual samples can simulate a variety of procedure structures of Olden benchmarks and this sample generation technique can provide sufficient samples for training model.

Ranking is a core problem for information retrieval since the performance of the search system is directly impacted by the accuracy of ranking results. Ranking model construction has been the focus of both the fields of information retrieval and machine learning, and learning to rank in particular has attracted much interest. Many ranking models have been proposed, for example, RankSVM is a state-of-the-art method for learning to rank and has been empirically demonstrated to be effective. However, most of the proposed methods do not consider about the significant differences between queries, only resort to a single function in ranking. In this paper, we present a novel ranking model named QoRank, which performs the learning task dependent on queries. We also propose a LSE (least-squares estimation) -based weighted method to aggregate the ranking lists produced by base decision functions as the final ranking. Comparison of QoRank with other ranking techniques is conducted, and several evaluation criteria are employed to evaluate its performance. Experimental results on the LETOR OHSUMED data set show that QoRank strikes a good balance of accuracy and complexity, and outperforms the baseline methods. © 2010 Wiley Periodicals, Inc.

Community detection is an important task for mining the structure and function of complex networks. Many pervious approaches are difficult to detect communities with arbitrary size and shape, and are unable to identify hubs and outliers. A recently proposed network clustering algorithm, SCAN, is effective and can overcome this difficulty. However, it depends on a sensitive parameter: minimum similarity threshold ε, but provides no automated way to find it. In this paper, we propose a novel density-based network clustering algorithm, called gSkeletonClu (graph-skeleton based clustering). By projecting a network to its Core-Connected Maximal Spanning Tree (CCMST), the network clustering problem is converted to finding core-connected components in the CCMST. We discover that all possible values of the parameter ε lie in the edge weights of the corresponding CCMST. By means of tree divisive or agglomerative clustering, our algorithm can find the optimal parameter ε and detect communities, hubs and outliers in large-scale undirected networks automatically without any user interaction. Extensive experiments on both real-world and synthetic networks demonstrate the superior performance of gSkeletonClu over the baseline methods.

Geographic routing is a promising approach for point-to-point routing in wireless sensor networks, but it requires the availability of geographic coordinates. Location devices like GPS do not work indoors and they are often not cost-effective for ubiquitous deployment on a large scale. While it is possible to manually configure coordinates for small sensor networks, it is infeasible to do the same for large-scale networks with thousands of nodes. We present Particle Swarm Virtual Coordinates (PSVC), a distributed virtual coordinate assignment algorithm that employs Particle Swarm Optimization to compute virtual coordinates for geographic routing. PSVC converges faster, achieves a lower hop stretch, and scales well up to large networks of 3,200 nodes compared to NoGeo. Also, PSVC makes no assumptions on the network topology and can naturally be extended to three-dimensional (3D) wireless sensor networks.

The characteristics of information resources are distributed, autonomous, heterogeneous and full of semantics in complex knowledge-based organizations at the era of knowledge economy. In order to realize efficient knowledge acquisition, representation, exchange, and sharing, we propose a novel concept of extended topic map, which extends the conventional topic map in structure. It embodies the multi-level, multi-granularity and other inherent relevant characteristics of knowledge. With the extended topic map as infrastructure, the framework of knowledge collaborative building in distributed scenario is achieved by the following four stages: knowledge extraction, local extended topic map generation, similarity calculation and global extended topic map generation. We give the key technologies of each stage, which take advantage of extended topic map-based techniques such as comprehensive information theory based similarity measure and merging strategies. Finally, an example of multi-resource knowledge integration based on extended topic map is given to elaborate the knowledge collaborative building process.

Ranking is a central problem for information retrieval systems, because the performance of an information retrieval system is mainly evaluated by the effectiveness of its ranking results. Learning to rank has received much attention in recent years due to its importance in information retrieval. This paper focuses on learning to rank in document retrieval and presents a ranking model named OrdRank that ranks documents with ordered multiple hyperplanes. Comparison of OrdRank with other state-of-the-art ranking techniques is conducted and several evaluation criteria are employed to evaluate its performance. Experimental results on the OHSUMED dataset show that OrdRank outperforms other methods, both in terms of quality of ranking results and efficiency.

This study proposes a novel method to group and organize search results. We apply statistical techniques to term co-occurrence information in a corpus to retrieve bi-grams firstly, and then combine bi-grams into n-grams. After eliminating redundant n-grams, the remaining ones are ranked and selected as cluster labels. Base clusters are constructed according to these cluster labels and then agglomerated into higher-level clusters. We refer to the proposed algorithm as CoHC (co-occurrence based hierarchical clustering). we compare CoHC with three other search results clustering (SRC) algorithms: suffix tree clustering (STC), Lingo, and Vivisimo. We also analyze the properties of cluster labels produced by different SRC algorithms. The experimental results show that our method outperforms the other three SRC algorithms, and is helpful to the user for browsing and locating the results of interest.

This paper discussed the disadvantages of the current search engines and built a meta-search engine. The system constructed the vector set, which composed of the vectors of each domain, by using the materials having been classified manually. When the user visited the Internet, the historical pages were recorded and downloaded. The system extracted the information from the pages and constructed the vector of every page. The distance between the page vector and the domain vector was calculated. The more the distance the more the relativity. The personalized model of the given user was built by the relativity. Due to the limit of the dictionary, the method of the word segmentation called "a domain independent dictionary free lexical acquisition model for Chinese document" was used. In this paper, some key technologies related to the system were discussed, such as extracting the class keywords, classifying methods, and the algorithm of the page value calculating. In the last paragraph, the future works, such as the storing of semi-structure information, and the calculating of the Web page's value were mentioned.

The XML-based meta-retrieval described in this paper is an integrated retrieval over multiple academic data sources on the premise that each data source has one web interface visible in the Internet environment. The goal of this model is to present an integrated retrieval interface in the Internet, to offer transparent accessing by formulating new queries suitable for heterogeneous data sources based on three adaptation rules, and to return the consolidated data results retrieved from multiple data sources. Technologies like eXtensible Markup Language(XML) and eXtensible Stylesheet Language Family(XSL) are used to facilitate the fulfillment of the goal. Experiment results prove that the model solve the heterogeneity of the data sources and provide transparent accessing for the end users.