Search

Automatically generating a survey draft is a challenge to text summarization research because it needs to select important sentences from important references in a large set of candidate papers for composing sections that are in line with section titles and different sections discuss the most relevant reference papers of different number, which are beyond the capability of previous text summarization approaches as they assume that all candidate papers should be included into one summary. This paper proposes an approach to generating survey draft according to a pattern consisting of sections with titles given by the user who requests the survey. The problem of generating each section can be divided into the following sub-problems: (1) rank the input scientific documents (in short documents) according to the title of a section, (2) determine the number of documents that are most relevant to the title, and (3) rank and select sentences from the selected documents according to the title. A position closeness distance of key word is proposed to rank a set of documents by measuring how closely two key words within section title are distributed within each document, which is used to rank the documents. The rationale is that the positions of the neighboring key words of a section title should be closer in more relevant documents than other words. As different sections have different number of selected documents, a method is proposed to determine the number of documents to be included into the current section based on the slope shape of the sorted rank curve of documents according to the section title. Based on the duality property of the closeness, ranks of sentences within a document can be directly obtained when the document is ranked according to the title of section, and both the importance and coherence of selected sentences can be reflected without extra calculation for ranking sentences. Experiments and manual evaluation show that the proposed methods achieve significant improvements compared with other approaches. The proposed approach is significant in applications as different surveys can be generated according to different patterns given by different users. [ABSTRACT FROM AUTHOR]

The key to realize advanced document summarization is semantic representation of documents. This paper investigates the role of Semantic Link Network in representing and understanding documents for multi-document summarization. It proposes a novel abstractive multi-document summarization framework by first transforming documents into a Semantic Link Network of concepts and events and then transforming the Semantic Link Network into the summary of the documents based on the selection of important concepts and events while keeping semantics coherence. Experiments on benchmark datasets show that the proposed summarization approach significantly outperforms relevant state-of-the-art baselines and the Semantic Link Network plays an important role in representing and understanding documents. [ABSTRACT FROM AUTHOR]

• Automatic and accurate evaluation of summary is a key problem of text summarization research. • A framework for evaluating summary from fidelity, conciseness, and coherence. • An evaluation method based on the semantic link network representation of text. • The semantic link network plays an important role in representing and analyzing texts. Automatic evaluation of summary is one of the basic problems of automatic text summarization research. The commonly used approaches evaluate the informativeness, conciseness and coherence of summary separately based on different representations with weak semantics such as n-gram and vector of words. By transforming text into semantic link network, this paper proposes a general framework for automatically evaluating summary from the following aspects: (1) fidelity , the extent of a summary that conveys the core of its source text; (2) conciseness , the extent of non-redundancy within summary and, (3) coherence , the extent of relatedness between representations within summary, which are based on a uniform semantic representation of text. Experiments on the evaluation of the summarization of scientific papers and news show that the proposed framework achieves comparable or higher correlations with human judgments than the popular evaluation models. This research also verifies the role of the semantic link network in representing and analysing texts. [ABSTRACT FROM AUTHOR]

Graphs are becoming increasingly dominant in modeling real-life networked data including social and biological networks, the WWW and the Semantic Web, etc. Graph pattern queries are useful for gathering information with expressive semantics from these graph-structured data. Current methods for graph pattern query processing have performance deficiency caused by inefficiencies of the underlying reachability index and costly merge-join operations on huge amounts of tuple-formatted intermediate results. To overcome the above problems, this paper contributes in the following aspects to boost graph pattern query evaluation. First, we propose an improved hop-based reachability indexing scheme 3-Hop* which gains faster reachability query evaluation, less indexing costs and better scalabilities than state-of-the-art hop-based methods. Second, we propose a two-stage node filtering algorithm based on 3-Hop* to answer tree pattern queries more efficiently. Tree pattern queries serve as the underlying facility for graph pattern query evaluation. Furthermore, we use a graph representation of the intermediate results during node filtering and final results enumeration. Experiments on real-life and synthetic datasets demonstrate the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

A text usually contains multiple semantic units corresponding to various reading requests from users. One semantic unit represents a topic that people are interested in reading. A meaningful combination of semantic units can represent a certain aspect of the text. This paper proposes a mechanism that can extract the semantic units from text according to the keywords representing users' interests and can organise semantic units into facets reflecting certain aspects of a text. The mechanism can display facets of a text with a set of operations. The proposed mechanism considers human reading process. With this mechanism, readers can quickly obtain the interested content from a large text. Experiments show its effectiveness and robustness. [ABSTRACT FROM AUTHOR]

We are living in a world of various kinds of social information networks with small-world and scale-free characteristics. It is still an intriguing problem for researchers to explain how and why so many obviously different networks emerge and share common intrinsic characteristics such as short diameter, higher cluster and power-law degree distribution. Most previous works studied the topology formation and information navigation of complex networks in separated models. In this paper, we propose a metric based range intersection model to explore the topology evolution and information navigation in a synthetic way. We model the network as a set of nodes in a distance metric space where each node has an ID and a range of neighbor information around its ID in the metric space. The range of a node can be seen as the local knowledge or information that the node has around its position in the metric space. The topology is formed by setting up a link between two nodes that have intersected ranges. Information navigation over the network is modeled as a greedy routing process using neighbor links and the distance metric. Different from previous models, we do not assume that nodes join the network one by one and set up link according to the degree distribution of existing nodes or distances between nodes. Range of node is the key factor determining the topology and navigation properties of a network. Moreover, as the ranges of nodes grow, the network evolves from a set of totally isolated nodes to a connected network. Thus, we can easily model the network evolutions in terms of the network size and the individual node information range using the range intersection model. A set of experiments shows that networks constructed using the range intersection model have the scale-free degree distribution, high cluster, short diameter, and high navigability properties that are owned by the real networks. [ABSTRACT FROM AUTHOR]

Abstract: Humans consciously and subconsciously establish various links, emerge semantic images and reason in mind, learn linking effect and rules, select linked individuals to interact, and form closed loops through links while co-experiencing in multiple spaces in lifetime. Machines are limited in these abilities although various graph-based models have been used to link resources in the cyber space. The following are fundamental limitations of machine intelligence: (1) machines know few links and rules in the physical space, physiological space, psychological space, socio space and mental space, so it is not realistic to expect machines to discover laws and solve problems in these spaces; and, (2) machines can only process pre-designed algorithms and data structures in the cyber space. They are limited in ability to go beyond the cyber space, to learn linking rules, to know the effect of linking, and to explain computing results according to physical, physiological, psychological and socio laws. Linking various spaces will create a complex space — the Cyber-Physical-Physiological-Psychological-Socio-Mental Environment CP3SME. Diverse spaces will emerge, evolve, compete and cooperate with each other to extend machine intelligence and human intelligence. From multi-disciplinary perspective, this paper reviews previous ideas on various links, introduces the concept of cyber-physical society, proposes the ideal of the CP3SME including its definition, characteristics, and multi-disciplinary revolution, and explores the methodology of linking through spaces for cyber-physical-socio intelligence. The methodology includes new models, principles, mechanisms, scientific issues, and philosophical explanation. The CP3SME aims at an ideal environment for humans to live and work. Exploration will go beyond previous ideals on intelligence and computing. [Copyright &y& Elsevier]

Abstract: Much research pursues machine intelligence through better representation of semantics. What is semantics? People in different areas view semantics from different facets although it accompanies interaction through civilization. Some researchers believe that humans have some innate structure in mind for processing semantics. Then, what the structure is like? Some argue that humans evolve a structure for processing semantics through constant learning. Then, how the process is like? Humans have invented various symbol systems to represent semantics. Can semantics be accurately represented? Turing machines are good at processing symbols according to algorithms designed by humans, but they are limited in ability to process semantics and to do active interaction. Super computers and high-speed networks do not help solve this issue as they do not have any semantic worldview and cannot reflect themselves. Can future cyber-society have some semantic images that enable machines and individuals (humans and agents) to reflect themselves and interact with each other with knowing social situation through time? This paper concerns these issues in the context of studying an interactive semantics for the future cyber-society. It firstly distinguishes social semantics from natural semantics, and then explores the interactive semantics in the category of social semantics. Interactive semantics consists of an interactive system and its semantic image, which co-evolve and influence each other. The semantic worldview and interactive semantic base are proposed as the semantic basis of interaction. The process of building and explaining semantic image can be based on an evolving structure incorporating adaptive multi-dimensional classification space and self-organized semantic link network. A semantic lens is proposed to enhance the potential of the structure and help individuals build and retrieve semantic images from different facets, abstraction levels and scales through time. [Copyright &y& Elsevier]

Cognitive cooperation is often neglected in current team software development processes. This issue becomes more important than ever when team members are globally distributed. This paper presents a notion of knowledge flow and the related management mechanism for realizing an ordered knowledge sharing and cognitive cooperation in a geographically distributed team software development process. The knowledge flow can carry and accumulate knowledge when it goes through from one team member to another. The coordination between the knowledge flow process and the workflow process of a development team provides a new way to improve traditional team software development processes. A knowledge grid platform has been implemented to support the knowledge flow management across the Internet. [Copyright &y& Elsevier]

To realize effective knowledge sharing in teamwork, this paper proposes a knowledge flow model for peer-to-peer knowledge sharing and management in cooperative teams. The model consists of the concepts, rules and methods about the knowledge flow, the knowledge flow process model, and the knowledge flow engine. A reference model for coordinating the knowledge flow process with the workflow process is suggested to provide an integrated approach to model teamwork process. We also discuss the peer-to-peer knowledge-sharing paradigm in large-scale teams and propose the approach for constructing a knowledge flow network from the corresponding workflow. The proposed model provides a new way to model and manage teamwork processes. [Copyright &y& Elsevier]

This paper proposes a knowledge grid model for sharing and managing globally distributed knowledge resources. The model organizes knowledge in a three-dimensional knowledge space, and provides a knowledge grid operation language, KGOL. Internet users can use the KGOL to create their knowledge grids, to put knowledge to them, to edit knowledge, to partially or wholly open their grids to all or some particular grids, and to get the required knowledge from the open knowledge of all the knowledge grids. The model enables people to conveniently share knowledge with each other when they work on the Internet. A software platform based on the proposed model has been implemented and used for knowledge sharing in research teams. [Copyright &y& Elsevier]

The Semantic Link Network is a general semantic model for modeling the structure and the evolution of complex systems. Various semantic links play different roles in rendering the semantics of complex system. One of the basic semantic links represents cause-effect relation, which plays an important role in representation and understanding. This paper verifies the role of the Semantic Link Network in representing the core of text by investigating the contribution of cause-effect link to representing the core of scientific papers. Research carries out with the following steps: (1) Two propositions on the contribution of cause-effect link in rendering the core of paper are proposed and verified through a statistical survey, which shows that the sentences on cause-effect links cover about 65% of key words within each paper on average. (2) An algorithm based on syntactic patterns is designed for automatically extracting cause-effect link from scientific papers, which recalls about 70% of manually annotated cause-effect links on average, indicating that the result adapts to the scale of data sets. (3) The effects of cause-effect link on four schemes of incorporating cause-effect link into the existing instances of the Semantic Link Network for enhancing the summarization of scientific papers are investigated. The experiments show that the quality of the summaries is significantly improved, which verifies the role of semantic links. The significance of this research lies in two aspects: (1) it verifies that the Semantic Link Network connects the important concepts to render the core of text; and, (2) it provides an evidence for realizing content services such as summarization, recommendation and question answering based on the Semantic Link Network, and it can inspire relevant research on content computing. [ABSTRACT FROM AUTHOR]

In recent years, we witness the increasing trend that more applications are developed by composing Web services. Services interact with each other in ways not necessarily foreseen during their development phase. In this setting, mismatches usually exist between services, and adapters are typically synthesized to reconcile mismatches occurring in certain interactions. The technique that identifies the most suitable provider service from a set of functionally equivalent candidates with respect to certain requirements specified by the requester is essential. To address this challenge, we propose a technique called adaptability assessment , which 1) provides a set of conditions that determines when service interactions can be conducted and 2) computes an adaptation degree that specifies to what extent a service protocol is adaptable to another service protocol. Adaptability assessment complements the techniques that synthesize adapters. Specifically, when adaptability assessment suggests that two service protocols can conduct some interactions according to the adaptation mechanisms of a certain adapter and these interactions can fulfill the requester's requirements, then the effort of synthesizing an adapter is beneficial to potential service interactions. As such, the requester can acknowledge whether his/her expected interactions can be conducted or not and under which conditions. This is important before conducting an interaction, particularly when this interaction is critical, long running, and nonrepeatable. [ABSTRACT FROM PUBLISHER]

It is important to help researchers find valuable papers from a large literature collection. To this end, many graph-based ranking algorithms have been proposed. However, most of these algorithms suffer from the problem of ranking bias. Ranking bias hurts the usefulness of a ranking algorithm because it returns a ranking list with an undesirable time distribution. This paper is a focused study on how to alleviate ranking bias by leveraging the heterogeneous network structure of the literature collection. We propose a new graph-based ranking algorithm, Mutual Rank, that integrates mutual reinforcement relationships among networks of papers, researchers, and venues to achieve a more synthetic, accurate, and less-biased ranking than previous methods. Mutual Rank provides a unified model that involves both intra- and inter-network information for ranking papers, researchers, and venues simultaneously. We use the ACL Anthology Network as the benchmark data set and construct the gold standard from computer linguistics course websites of well-known universities and two well-known textbooks. The experimental results show that Mutual Rank greatly outperforms the state-of-the-art competitors, including Page Rank, HITS, Co Rank, Future Rank, and P- Rank, in ranking papers in both improving ranking effectiveness and alleviating ranking bias. Rankings of researchers and venues by Mutual Rank are also quite reasonable. [ABSTRACT FROM AUTHOR]