The Experts below are selected from a list of 2415 Experts worldwide ranked by ideXlab platform
Hai Zhuge - One of the best experts on this subject based on the ideXlab platform.
-
abstractive multi document summarization based on Semantic Link Network
2021Co-Authors: Hai ZhugeAbstract: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.
-
cyber physical social Semantic Link Network
2020Co-Authors: Hai ZhugeAbstract:Is there any cause-effect Link between thinking, experiencing and knowledge? This problem has challenged philosophers and scientists for centuries. Understanding and representing reality is a key step toward finding the Link. Semantics modelling is an approach to understanding and representing reality.
-
the influence of Semantic Link Network on the ability of question answering system
2020Co-Authors: Hai ZhugeAbstract:Abstract Semantic Link Network plays an important role in representing and understanding text. This paper investigates the influence of Semantic Links on the basic abilities of a type of QA system that extracts answers from a range of texts (answer range). Research concerns how Semantic Links influence the answer range and the performance of this type of QA system. Research also concerns the ability to answering different types of questions and supporting different patterns of answering questions. Based on the Semantic Link Network extracted from Wikipedia, an experimental QA system is developed to answer questions according to a range of pages in Wikipedia. Research reached the following results: (1) the answer range and the Semantic Link Network influence each other: keeping a certain range of performance, increase one can decrease the request of the other; and, (2) the Semantic Link Network can enhance the ability of QA system in answering questions and supporting patterns of answering questions covered by Semantic Link Network.
-
probabilistic inference on uncertain Semantic Link Network and its application in event identification
2020Co-Authors: Hai ZhugeAbstract:Abstract The Probabilistic Semantic Link Network (P-SLN) is a model for enhancing the ability of Semantic Link Network in representing uncertainty. Probabilistic inference over uncertain Semantic Links can process the likelihood and consistency of uncertain Semantic Links. This work develops the P-SLN model by incorporating probabilistic inference rules and consistency constraints. Two probabilistic inference mechanisms are incorporated into the model. The application of probabilistic inference on SLN of events for joint event identification verifies the effectiveness of the proposed model.
-
Semantic Link Network for understanding and representing reality in cyber physical social space a model for managing covid 19 pandemic
2020Co-Authors: Hai ZhugeAbstract:Humans evolve with understanding reality and discovering, applying and developing knowledge. An approach to understanding reality is to observe and deal with unknown phenomena and then discover, interpret and verify the underlying principles and rules. Link and dimension are basic means for understanding and representing reality.
Yunchuan Sun - One of the best experts on this subject based on the ideXlab platform.
-
theory for Semantic relation computing and its application in Semantic Link Network
2012Co-Authors: Yunchuan Sun, Hongli Yan, Rongfang BieAbstract:Semantic relation among different objects is one of the most important kinds of Semantics which plays the primary role for people and intelligent systems in grasping the situation accurately in the context of connected systems. The Semantic relations are viewed as the most important elements in most existing information models (such as ER model, RDF and SLN) during the mapping from the physical world into the cyber world, where efficient ways of representation for Semantic relations are developed. However, all these models deal with the Semantic relations in a simple and intuitive way. Few works go deep into the study of Semantic relations from a mathematic view. This paper aims at exploring a mathematic theory of the Semantic relations between objects including representing methods, normal forms of operations, Semantic orthogonal basis of the Semantic relations. We also discuss the reasoning mechanism based on the proposed theory. The applications of the developed theory in Semantic Link Network are discussed finally.
-
Advances of the Semantic Link Network
2012Co-Authors: Shenling Wang, Yunchuan Sun, Hongyang Zhang, Xiaofeng Yu, Rongfang BieAbstract:The Semantic Link Network (SLN) is a loosely coupled Semantic data model for managing the Network resources. A SLN consists of three components: a set of Semantic nodes, a set of Semantic Links, and a set of reasoning rules. Semantic nodes can be objects of any types. Semantic Links reflect the Semantic relations among objects. Reasoning rules, which describe the internal relations among Semantic Links, are used to derive new Semantic Links hidden behind. SLN is designed to establish Semantic relationships among various resources for extending the current hyperLink Network to a Semantic-rich Network. In this paper, we conduct a survey on the research of SLN from its theory and applications. Furthermore, the future trends of SLN and it's potential applications in future Internet of Things are discussed.
-
weaving the Semantic Link Network of events
2010Co-Authors: Junsheng Zhang, Yunchuan SunAbstract:Event processing is a significant evolution in the field of information technology. Semantic Link Network (SLN) is a Semantic data model for managing resources and their Semantic relations. This paper proposes a two-layered SLN model for event processing: the matter level and the event level. The event SLN aims to record and manage the evolving process of the matter level. We propose a domain independent schema for the event SLN consisting of a set of primary Link types and a set of reasoning rules. The model is useful in data encapsulating, knowledge retrieving, knowledge flow discovery, and intelligent applications for the internet of things.
-
an analogy reasoning model for Semantic Link Network
2010Co-Authors: Junsheng Zhang, Yunchuan SunAbstract:Analogy reasoning is one of the most important reasoning means of human thinking. How to implement analogy reasoning automatically with computers has been a hot topic in artificial intelligence and psychology. This paper proposes a mathematic model for analogy reasoning over Semantic Link Network (SLN). We propose a reliable analogy theorem over SLN based on the category theory and some algorithms have been developed to implement analogical reasoning by constructing a Semantic functor between SLNs. Meanwhile, we also discuss some analogy conjecture models and algorithms which may be unreliable but useful to giving some suggestions for solving a given problem. A study cases is proposed to show the validity and efficiency of the proposed theorem and the algorithms.
-
The schema theory for Semantic Link Network
2010Co-Authors: Hai Zhuge, Yunchuan SunAbstract:The Semantic Link Network (SLN) is a loosely coupled Semantic data model for managing Web resources. Its nodes can be any type of resource. Its edges can be any Semantic relation. Potential Semantic Links can be derived out according to reasoning rules on Semantic relations. This paper proposes the schema theory for the SLN, including the concepts, rule-constraint normal forms, and relevant algorithms. The theory provides the basis for normalized management of Semantic Link Network. A case study demonstrates the proposed theory. © 2009.
Yuhui Qiu - One of the best experts on this subject based on the ideXlab platform.
-
micro blogging based Network growth model of Semantic Link Network
2014Co-Authors: Wei Ren, Yuhui QiuAbstract:This paper studies the Network model in SLN by applying the methodology of social Network to a widely accepted, real-life user interactive Network scenario. The data and experiments are based on micro-blogging (Sina Weibo). Results show that the statistic properties of SLN are in close analogy with that of social Network. Contrary to our normal understanding, some nodes with too much Semantics (especially under one category) are in decreased chances of having Links from newly added nodes.
-
user interaction based Network growth model of Semantic Link Network
2010Co-Authors: Wei Ren, Zhixing Huang, Yuhui QiuAbstract:The social Network of the Internet is interpreted as the consequences of invisible connection between humans. In the graph based studies the nodes are human beings and the edges represent various social relationships. SLN is a loosely coupled, self-organized Semantic data model that Link resources Semantically. The interactions among users can be interpreted via SLN formation and evolution The interactive as well as intertwined behaviours are the foundation of Network itself, at the same time, they shape the way how and where the Network will evolve, enrich the Semantics of the Network and expand the Network scale. This paper proposes a Network growth model of SLN based on the Semantics similarity and popularity of nodes. In our model, the nodes are Twitter blogs and are with Semantics, the Links are subscribing hyperLinks between blogs. The probability of Link establishment between two nodes then calculated from the parameters given above. The data and experiments are based on Twitter blogs, which are the continuous results of interactions by users globally. We crawled the publicly accessible user interaction on blogs, obtaining a portion of the Network’s Links between blogs and the hierarchy of each blog may exist in the whole scenarios. Results show that the statistic properties of SLN are in close analogy with that of social Network. The studied Network contains a number of high-degree nodes, these nodes are the cores which small groups strongly clustered, and low-degree nodes at the fringes of the Network. However, some nodes with too much Semantics (especially under one category) are in decreased chances of having Links from newly added nodes. The reason may lies in that the over-abundant Semantics remains confusion for knowledge acquiring.
-
the fuzzy Semantic relations in Semantic Link Network
2010Co-Authors: Lunqian Duan, Zhurong Zhou, Yuhui QiuAbstract:The Semantic Link Network (SLN) is a directed Network consisting of Semantic nodes and Semantic Links between nodes. A Semantic Link directed from one node to another can be represented as a pointer labeled with a Semantic relation. Since the proposed of SLN, it gets widely used, and increasingly becomes a study hotspot. SLN do not consider the fuzzy of Semantic nodes and Semantic relations, so that it can not express the fuzzy Semantics, which leads to lack of accuracy. This shortcoming is more obvious when we apply SLN in the domain of image retrieval and community detection. This paper introduced fuzzy theory into SLN, proposed a five-layer fuzzy based model for Fuzzy Semantic Link Network, and used the fuzzy degree to measure the fuzzy Semantics relations. The experiment results showed that the application of F_SLN to image retrieval is effective, when dealing with fuzzy issues.
-
a multiple perspective approach to constructing and aggregating citation Semantic Link Network
2010Co-Authors: Zhixing Huang, Yuhui QiuAbstract:Various kinds of Semantic relationships exist among scientific literatures which worth to be explored. This paper proposes a Citation Semantic Link Network (C-SLN) to describe the Semantic information over the literature citation Networks. A framework of the construction of C-SLN is represented by integrating several NLP methods. The methods of aggregating a C-SLN and the algorithms of discovering opinion communities in a C-SLN are also discussed. Based on a multi-perspective exploration on the C-SLN, we can effectively find articles of high importance, aggregate the function of citations and detect opinion communities among scientific documents.
-
Semantic Link Network portal for multimedia content recommendation
2009Co-Authors: Zuqin Chen, Yuhui QiuAbstract:Recently, Web-based news publishing is evolving fast, as many other Internet services, and nowadays this service is trying to adapt information in manners that better fit user’s interests and capabilities in the digital space. In this paper, we propose a Semantic Link Network portal for multimedia content recommendation. The portal is based on Semantic Link Network technologies and attempts to build up a multimedia repository that makes the media house more productive. The goal of the portal is to integrate different kinds of content in Semantic Link Network through Semantically annotated audio transcriptions, and other media metadata. In particular, it provides user interface that allows user to interact with and recommend content in an efficient and effective way.
Xiaoping Sun - One of the best experts on this subject based on the ideXlab platform.
-
summarization of scientific paper through reinforcement ranking on Semantic Link Network
2018Co-Authors: Xiaoping Sun, Hai ZhugeAbstract:The Semantic Link Network is a Semantics modeling method for effective information services. This paper proposes a new text summarization approach that extracts Semantic Link Network from scientific paper consisting of language units of different granularities as nodes and Semantic Links between the nodes, and then ranks the nodes to select Top-k sentences to compose summary. A set of assumptions for reinforcing representative nodes is set to reflect the core of paper. Then, Semantic Link Networks with different types of node and Links are constructed with different combinations of the assumptions. Finally, an iterative ranking algorithm is designed for calculating the weight vectors of the nodes in a converged iteration process. The iteration approximately approaches a stable weight vector of sentence nodes, which is ranked to select Top-k high-rank nodes for composing summary. We designed six types of ranking models on Semantic Link Networks for evaluation. Both objective assessment and intuitive assessment show that ranking Semantic Link Network of language units can significantly help identify the representative sentences. This paper not only provides a new approach to summarizing text based on the extraction of Semantic Links from text but also verifies the effectiveness of adopting the Semantic Link Network in rendering the core of text. The proposed approach can be applied to implementing other summarization applications such as generating an extended abstract, the mind map, and the bulletin points for making the slides of a given paper. It can be easily extended by incorporating more Semantic Links to improve text summarization and other information services.
-
the contribution of cause effect Link to representing the core of scientific paper the role of Semantic Link Network
2018Co-Authors: Hai Zhuge, Xiaoping Sun, Mengyun CaoAbstract: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.
-
sentence ranking with the Semantic Link Network in scientific paper
2015Co-Authors: Jiao Tian, Mengyun Cao, Xiaoping Sun, Jin Liu, Hai ZhugeAbstract:Sentence ranking is one of the most important research issues in text analysis. It can be used in text summarization and information retrieval. Graph-based methods are a common way of ranking and extracting sentences. In graph based methods, sentences are nodes of graph and edges are built based on the sentence similarities or on sentence co-occurrence relationship. PageRank style algorithms can be applied to get sentence ranks. In this paper, we focus on how to rank sentences in a single scientific paper. A scientific literature has more structural information than general texts and this structural information has not been fully explored yet in graph based ranking models. We investigated several different methods that used the is-part-of Link on paragraph and section and similar Link and co-occurrence Link to construct a heterogeneous graph for ranking sentences. We conducted experiments on these methods to compare the results on sentence ranking. It shows that structural information can help identify more representative sentences.
-
osln an object oriented Semantic Link Network language for complex object description and operation
2010Co-Authors: Xiaoping SunAbstract:As the Semantic data grows rapidly on the Web, we need flexible and powerful tools to describe and manage complex data, information and knowledge structures on the Web. Basic structural Semantic information of classes, instances, properties and relationships can be described using Semantic Web languages. More and more applications need to describe and manage objects with complex structures, operations and interactions on the Web. In this paper, we introduce an Object-Oriented Semantic Link Network language OSLN that can be used to define complex objects with rich object-oriented Semantics on the Web. In OSLN, objects are the basic Semantic elements with internal members and functions that are declared to express attributes and Semantic processes. Semantic Links are defined to describe Semantic relationships among objects. Many important features from traditional object-oriented programming languages are incorporated into OSLN, allowing users to write Semantic programs for not only describing complex structures of objects but also defining object operations and manipulations. OSLN enables users to write Semantic scripts like using traditional programming languages, which will improve both user experiences and application areas of the Semantic Web technologies.
-
complex queries for heterogeneous resources on a structured p2p Semantic Link Network
2008Co-Authors: Hai Zhuge, Xue Chen, Xiaoping SunAbstract:This paper investigates the issue of realizing complex queries for heterogeneous resources on dynamic and large-scale decentralized Networks. We build a distributed index on a structured P2P Network HRing to represent Semantic relations between resources to support complex query, and establish Semantic Links among nodes of P2P Network to realize ef ficient routing of queries. Incorporating distributed index, Semantic Links and HRing forms a structured P2P Semantic Link Network (SemHRing). Current search engines are limited in abilit y to support relational queries, which are often required in real applications. SemHRing can support keyword queries and relational queries while guaranteeing high performance and low maintenance cost as well as high robustness. SemHRing can be a feasible solution to the distributed storage system f or next- generation search engines.
Zhixing Huang - One of the best experts on this subject based on the ideXlab platform.
-
designing a novel linear time graph kernel for Semantic Link Network
2015Co-Authors: Li Peng, Hai Zhuge, Zhixing Huang, Qiaoli Huang, Zhiying ZhangAbstract:Graph is an efficient tool for representing structured data such as proteins, molecular compounds, and social Networks. Graph kernel is a technique to measure the similarity between graphs. However, existing graph kernels still have several limitations: 1 Semantics on Link is ignored; 2 node is associated with single label; 3 most graph kernels require more than cubic time, which is still computationally expensive; and, 4 there is seldom consideration of handling the graph comparison when the number of node types becomes huge. In this paper, we utilize Semantic Link Network SLN to represent complex structured data with richer Semantic information. Topic model is employed for dimension reduction and tagging each node with multiple labels. And a novel linear-time graph kernel for SLN is designed to calculate the similarity between two SLNs. This work remedies the limitations of the conventional graph kernels. The effectiveness and efficiency of this approach are evaluated by the document classification task on public corpora. Empirical results demonstrate that the proposed method can achieve better performance than the traditional topic model-based classification approach. Copyright © 2015 John Wiley & Sons, Ltd.
-
a new approach to embedding Semantic Link Network with word2vec binary code
2015Co-Authors: Yanhong Yuan, Yao Liu, Qiaoli Huang, Zhixing HuangAbstract:Graph-structured data has come into wide use in various fields where graphs are the natural data structure to model Networks. Therefore, the comparison between two graphs becomes a research focus. Traditional approaches for graph comparison face the common problem: either increasing the runtime for large graphs or simplifying the representation of graphs which ignores part of their topological information. In this paper, we build the Semantic Link Network (SLN) to represent documents and introduce a new graph kernel to compare their similarity. Where the graph representations are built according to the co-occurrence relations. And then, the Semantic Link Network will be generated by embedding the rich Semantic information which is obtained by neural Network language model. Finally, a new graph kernel will be introduced and used to compare the similarity between the Semantic Link Network of documents. The effectiveness and efficiency of this method are evaluated by the document classification task on public corpora and empirical results suggest that the proposed method can achieve better performance than the traditional classification approaches.
-
designing a hierarchical graph kernel for Semantic Link Network
2013Co-Authors: Zhiying Zhang, Li Peng, Zhixing HuangAbstract:One of the most important abilities of human is cluster and classify similar things, which makes people could better understand the nature, easier establish and manage the social society. How to model things like people and how to compute the similarities between models are two major problems need to be solved to make the machine has this ability. For the first problem, the Semantic Link Network (SLN) could be a appropriate choice, however, the challenge is how to compute the similarities between SLNs. In this paper, we design a hierarchical graph kernel for SLNs to solve this challenge. We evaluate the practical performance of our kernels on a task of detecting Semantic similar relationships between texts. The result show that the detection results of Semantic node hierarchical kernel is most similar to human's.
-
Using Quadtree-Based Semantic Link Network for Image Classification
2013Co-Authors: Li Peng, Zhixing HuangAbstract:Bag-of-words model is widely utilized for representing images in a Semantic intermediate manner. However traditional visual words are orderless without information with regard to co-occurrences of them as well as their spatial distributions. Spatial pyramid matching provides an effective way to preserve partly spatial information within images, but ignores geometric relations between visual words. By means of quadrant division, this paper proposed a novel methodology called quadtree-based Semantic Link Network(qt-SLN) to represent images in the form of Semantic Network to keep the structural and topological information of an image. The task of image classification then becomes one of classifying graphs which can be implemented with graph kernels defined on different structured data. In addition, co-occurrences of visual words are also modeled using Pointwise Mutual Information(PMI), which is exploited as a substitution matrix in approximate graph matching after normalization. The experimental results show that incorporating structural relations and co-occurrences of visual words allows for a more Semantical framework of classification task.
-
user interaction based Network growth model of Semantic Link Network
2010Co-Authors: Wei Ren, Zhixing Huang, Yuhui QiuAbstract:The social Network of the Internet is interpreted as the consequences of invisible connection between humans. In the graph based studies the nodes are human beings and the edges represent various social relationships. SLN is a loosely coupled, self-organized Semantic data model that Link resources Semantically. The interactions among users can be interpreted via SLN formation and evolution The interactive as well as intertwined behaviours are the foundation of Network itself, at the same time, they shape the way how and where the Network will evolve, enrich the Semantics of the Network and expand the Network scale. This paper proposes a Network growth model of SLN based on the Semantics similarity and popularity of nodes. In our model, the nodes are Twitter blogs and are with Semantics, the Links are subscribing hyperLinks between blogs. The probability of Link establishment between two nodes then calculated from the parameters given above. The data and experiments are based on Twitter blogs, which are the continuous results of interactions by users globally. We crawled the publicly accessible user interaction on blogs, obtaining a portion of the Network’s Links between blogs and the hierarchy of each blog may exist in the whole scenarios. Results show that the statistic properties of SLN are in close analogy with that of social Network. The studied Network contains a number of high-degree nodes, these nodes are the cores which small groups strongly clustered, and low-degree nodes at the fringes of the Network. However, some nodes with too much Semantics (especially under one category) are in decreased chances of having Links from newly added nodes. The reason may lies in that the over-abundant Semantics remains confusion for knowledge acquiring.
