D. Schneider, Denny Stohr, J. Tingvold, A. B. Amundsen, Lydia Weiland, S. Kopf, W. Effelsberg, A. Scherp
Multimedia documents like PowerPoint presentations or Flash documents are widely adopted in the Internet and exist in context of lots of different topics. However, so far there is no user friendly way to explore and search for this content. The aim of this work is to address this issue by developing a new, easy-to-use user interface approach and prototype search engine. Our system is called fulgeo and specifically focuses on a suitable multimedia interface for visualizing the query results of semantically-enriched Flash documents.
{"title":"Fulgeo -- Towards an Intuitive User Interface for a Semantics-Enabled Multimedia Search Engine","authors":"D. Schneider, Denny Stohr, J. Tingvold, A. B. Amundsen, Lydia Weiland, S. Kopf, W. Effelsberg, A. Scherp","doi":"10.1109/ICSC.2014.52","DOIUrl":"https://doi.org/10.1109/ICSC.2014.52","url":null,"abstract":"Multimedia documents like PowerPoint presentations or Flash documents are widely adopted in the Internet and exist in context of lots of different topics. However, so far there is no user friendly way to explore and search for this content. The aim of this work is to address this issue by developing a new, easy-to-use user interface approach and prototype search engine. Our system is called fulgeo and specifically focuses on a suitable multimedia interface for visualizing the query results of semantically-enriched Flash documents.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114061580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Big data processing is one of the hot scientific issues in the current social development. MapReduce is an important foundation for big data processing. In this paper, we propose a semantic++ MapReduce. This study includes four parts. (1) Semantic++ extraction and management for big data. We will do research about the automatically extracting, labeling and management methods for big data's semantic++ information. (2) SMRPL (Semantic++ MapReduce Programming Language). It is a declarative programming language which is close to the human thinking and be used to program for big data's applications. (3) Semantic++ MapReduce compilation methods. (4) Semantic++ MapReduce computing technology. It includes three parts. 1) Analysis of semantic++ index information of the data block, the description of the semantic++ index structure and semantic++ index information automatic loading method. 2) Analysis of all kinds of semantic++ operations such as semantic++ sorting, semantic++ grouping, semantic+++ merging and semantic++ query in the map and reduce phases. 3) Shuffle scheduling strategy based on semantic++ techniques. This paper's research will optimize the MapReduce and enhance its processing efficiency and ability. Our research will provide theoretical and technological accumulation for intelligent processing of big data.
{"title":"A Semantic++ MapReduce: A Preliminary Report","authors":"Guigang Zhang, Jian Wang, Weixing Huang, C. Li, Yong Zhang, Chunxiao Xing","doi":"10.1109/ICSC.2014.63","DOIUrl":"https://doi.org/10.1109/ICSC.2014.63","url":null,"abstract":"Big data processing is one of the hot scientific issues in the current social development. MapReduce is an important foundation for big data processing. In this paper, we propose a semantic++ MapReduce. This study includes four parts. (1) Semantic++ extraction and management for big data. We will do research about the automatically extracting, labeling and management methods for big data's semantic++ information. (2) SMRPL (Semantic++ MapReduce Programming Language). It is a declarative programming language which is close to the human thinking and be used to program for big data's applications. (3) Semantic++ MapReduce compilation methods. (4) Semantic++ MapReduce computing technology. It includes three parts. 1) Analysis of semantic++ index information of the data block, the description of the semantic++ index structure and semantic++ index information automatic loading method. 2) Analysis of all kinds of semantic++ operations such as semantic++ sorting, semantic++ grouping, semantic+++ merging and semantic++ query in the map and reduce phases. 3) Shuffle scheduling strategy based on semantic++ techniques. This paper's research will optimize the MapReduce and enhance its processing efficiency and ability. Our research will provide theoretical and technological accumulation for intelligent processing of big data.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"97 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128035995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a simple approach to handle recursive SPARQL queries, that is, nested queries that may contain references to the query itself. This powerful feature is obtained by implementing a custom SPARQL function that takes a SPARQL query as a parameter and executes it over a specified endpoint. The behaviour is similar to the SPARQL 1.1 SERVICE clause, with a few fundamental differences: (1) the query passed as argument can be arbitrarily complex, (2) being a string, the query can be created at runtime in the calling (outer) query, and (3) it can reference to itself, enabling recursion. These features transform the SPARQL language into a Turing-equivalent one without introducing special constructs or needing another interpreter implemented on the endpoint server engine. The feature is implemented using the standard Estensible Value Testing described in the recommendations since 1.0, therefore, our proposal is standard compliant and also compatible with older endpoints not supporting 1.1 Specifications, where it can be also a replacement for the missing SERVICE clause.
{"title":"Computing Recursive SPARQL Queries","authors":"M. Atzori","doi":"10.1109/ICSC.2014.54","DOIUrl":"https://doi.org/10.1109/ICSC.2014.54","url":null,"abstract":"We present a simple approach to handle recursive SPARQL queries, that is, nested queries that may contain references to the query itself. This powerful feature is obtained by implementing a custom SPARQL function that takes a SPARQL query as a parameter and executes it over a specified endpoint. The behaviour is similar to the SPARQL 1.1 SERVICE clause, with a few fundamental differences: (1) the query passed as argument can be arbitrarily complex, (2) being a string, the query can be created at runtime in the calling (outer) query, and (3) it can reference to itself, enabling recursion. These features transform the SPARQL language into a Turing-equivalent one without introducing special constructs or needing another interpreter implemented on the endpoint server engine. The feature is implemented using the standard Estensible Value Testing described in the recommendations since 1.0, therefore, our proposal is standard compliant and also compatible with older endpoints not supporting 1.1 Specifications, where it can be also a replacement for the missing SERVICE clause.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"2017 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125647667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Basharat, I. Arpinar, Shima Dastgheib, Ugur Kursuncu, K. Kochut, Erdogan Dogdu
Crowd sourcing is an emerging paradigm to exploit the notion of human-computation for solving various computational problems, which cannot be accurately solved solely by the machine-based solutions. We use crowd sourcing for large-scale link management in the Semantic Web. More specifically, we develop Crowd Link, which utilizes crowd workers for verification and creation of triples in Linking Open Data (LOD). LOD incorporates the core data sets in the Semantic Web, yet is not in full conformance with the guidelines for publishing high quality linked data on the Web. Our approach can help in enriching and improving quality of mission-critical links in LOD. Scalable LOD link management requires a hybrid approach, where human intelligent and machine intelligent tasks interleave in a workflow execution. Likewise, many other crowd sourcing applications require a sophisticated workflow specification not only on human intelligent tasks, but also machine intelligent tasks to handle data and control-flow, which is strictly deficient in the existing crowd sourcing platforms. Hence, we are strongly motivated to investigate the interplay of crowd sourcing, and semantically enriched workflows for better human-machine cooperation in task completion. We demonstrate usefulness of our approach through various link creation and verification tasks, and workflows using Amazon Mechanical Turk. Experimental evaluation demonstrates promising results in terms of accuracy of the links created, and verified by the crowd workers.
{"title":"CrowdLink: Crowdsourcing for Large-Scale Linked Data Management","authors":"A. Basharat, I. Arpinar, Shima Dastgheib, Ugur Kursuncu, K. Kochut, Erdogan Dogdu","doi":"10.1109/ICSC.2014.14","DOIUrl":"https://doi.org/10.1109/ICSC.2014.14","url":null,"abstract":"Crowd sourcing is an emerging paradigm to exploit the notion of human-computation for solving various computational problems, which cannot be accurately solved solely by the machine-based solutions. We use crowd sourcing for large-scale link management in the Semantic Web. More specifically, we develop Crowd Link, which utilizes crowd workers for verification and creation of triples in Linking Open Data (LOD). LOD incorporates the core data sets in the Semantic Web, yet is not in full conformance with the guidelines for publishing high quality linked data on the Web. Our approach can help in enriching and improving quality of mission-critical links in LOD. Scalable LOD link management requires a hybrid approach, where human intelligent and machine intelligent tasks interleave in a workflow execution. Likewise, many other crowd sourcing applications require a sophisticated workflow specification not only on human intelligent tasks, but also machine intelligent tasks to handle data and control-flow, which is strictly deficient in the existing crowd sourcing platforms. Hence, we are strongly motivated to investigate the interplay of crowd sourcing, and semantically enriched workflows for better human-machine cooperation in task completion. We demonstrate usefulness of our approach through various link creation and verification tasks, and workflows using Amazon Mechanical Turk. Experimental evaluation demonstrates promising results in terms of accuracy of the links created, and verified by the crowd workers.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134485933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vector Symbolic Architectures (VSA) are methods designed to enable distributed representation and manipulation of semantically-structured information, such as natural languages. Recently, a new VSA based on multiplication of distributed vectors by random matrices was proposed, this is known as Matrix-Binding-of-Additive-Terms (MBAT). We propose an enhancement that introduces an important additional feature to MBAT: the ability to 'unbind' symbols. We show that our method, which exploits the inherent properties of orthogonal matrices, imparts MBAT with the 'question answering' ability found in other VSAs. We compare our results with another popular VSA that was recently demonstrated to have high utility in brain-inspired machine learning applications.
{"title":"Enabling 'Question Answering' in the MBAT Vector Symbolic Architecture by Exploiting Orthogonal Random Matrices","authors":"M. Tissera, M. McDonnell","doi":"10.1109/ICSC.2014.38","DOIUrl":"https://doi.org/10.1109/ICSC.2014.38","url":null,"abstract":"Vector Symbolic Architectures (VSA) are methods designed to enable distributed representation and manipulation of semantically-structured information, such as natural languages. Recently, a new VSA based on multiplication of distributed vectors by random matrices was proposed, this is known as Matrix-Binding-of-Additive-Terms (MBAT). We propose an enhancement that introduces an important additional feature to MBAT: the ability to 'unbind' symbols. We show that our method, which exploits the inherent properties of orthogonal matrices, imparts MBAT with the 'question answering' ability found in other VSAs. We compare our results with another popular VSA that was recently demonstrated to have high utility in brain-inspired machine learning applications.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132504520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents our experiment on the "Badea" system. A system designed for the automated extraction of semantic relations from text using a seed ontology and a pattern based approach. We describe the experiment using a set of Arabic language corpora for extracting the antonym semantic relation. Antonyms from the seed ontology are used to extract patterns from the corpora, these patterns are then used to discover new antonym pairs, thus enriching the ontology. Evaluation results show that the system was successful in enriching the ontology with over 400% increase in size. The results also showed that only 2.7% of the patterns were useful in extracting new antonyms, and thus recommendations for pattern scoring are presented in this paper.
{"title":"A Pattern-Based Approach to Semantic Relation Extraction Using a Seed Ontology","authors":"M. Al-Yahya, L. Aldhubayi, Sawsan Al-Malak","doi":"10.1109/ICSC.2014.42","DOIUrl":"https://doi.org/10.1109/ICSC.2014.42","url":null,"abstract":"This paper presents our experiment on the \"Badea\" system. A system designed for the automated extraction of semantic relations from text using a seed ontology and a pattern based approach. We describe the experiment using a set of Arabic language corpora for extracting the antonym semantic relation. Antonyms from the seed ontology are used to extract patterns from the corpora, these patterns are then used to discover new antonym pairs, thus enriching the ontology. Evaluation results show that the system was successful in enriching the ontology with over 400% increase in size. The results also showed that only 2.7% of the patterns were useful in extracting new antonyms, and thus recommendations for pattern scoring are presented in this paper.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133935582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Technologies based on the internet are improving continuously and so are the harmful websites such as pornography or illegal gambling websites. In addition, it is the characteristics of websites that the changes made to the web address or its contents take effect almost instantaneously. Therefore, it is not easy to identify harmful websites from those that are not. There are two ways to make such decision: manual examination and automated searching for certain texts, videos, or sounds. These two methods require a lot of time. In this paper we propose a method for identifying harmful websites by analyzing the relationship between websites instead of the contents.
{"title":"Semantic Approach for Identifying Harmful Sites Using the Link Relations","authors":"Junghoon Shin, Sangjun Lee, Taehyung Wang","doi":"10.1109/ICSC.2014.53","DOIUrl":"https://doi.org/10.1109/ICSC.2014.53","url":null,"abstract":"Technologies based on the internet are improving continuously and so are the harmful websites such as pornography or illegal gambling websites. In addition, it is the characteristics of websites that the changes made to the web address or its contents take effect almost instantaneously. Therefore, it is not easy to identify harmful websites from those that are not. There are two ways to make such decision: manual examination and automated searching for certain texts, videos, or sounds. These two methods require a lot of time. In this paper we propose a method for identifying harmful websites by analyzing the relationship between websites instead of the contents.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131994164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We investigate user requirements regarding the interface design for a semantic multimedia search and retrieval based on a prototypical implementation of a search engine for multimedia content on the web. Thus, unlike existing image search engines and video search engines, we are interested in true multimedia content combining different media assets into multimedia documents like PowerPoint presentations and Flash files. In a user study with 20 participants, we conducted a formative evaluation based on the think-aloud method and semi-structured interviews in order to obtain requirements to a future web search engine for multimedia content. The interviews are complemented by a paper-and-pencil questionnaire to obtain quantitative information and present mockups demonstrating the user interface of a future multimedia search and retrieval engine.
{"title":"Requirements Elicitation Towards a Search Engine for Semantic Multimedia Content","authors":"Lydia Weiland, Felix Hanser, A. Scherp","doi":"10.1109/ICSC.2014.35","DOIUrl":"https://doi.org/10.1109/ICSC.2014.35","url":null,"abstract":"We investigate user requirements regarding the interface design for a semantic multimedia search and retrieval based on a prototypical implementation of a search engine for multimedia content on the web. Thus, unlike existing image search engines and video search engines, we are interested in true multimedia content combining different media assets into multimedia documents like PowerPoint presentations and Flash files. In a user study with 20 participants, we conducted a formative evaluation based on the think-aloud method and semi-structured interviews in order to obtain requirements to a future web search engine for multimedia content. The interviews are complemented by a paper-and-pencil questionnaire to obtain quantitative information and present mockups demonstrating the user interface of a future multimedia search and retrieval engine.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124851384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we propose a simple and completely automatic methodology for analyzing sentiment of users in Twitter. Firstly, we built a Twitter corpus by grouping tweets expressing positive and negative polarity through a completely automatic procedure by using only emoticons in tweets. Then, we have built a simple sentiment classifier where an actual stream of tweets from Twitter is processed and its content classified as positive, negative or neutral. The classification is made without the use of any pre-defined polarity lexicon. The lexicon is automatically inferred from the streaming of tweets. Experimental results show that our method reduces human intervention and, consequently, the cost of the whole classification process. We observe that our simple system captures polarity distinctions matching reasonably well the classification done by human judges.
{"title":"Automatic Unsupervised Polarity Detection on a Twitter Data Stream","authors":"D. Terrana, A. Augello, G. Pilato","doi":"10.1109/ICSC.2014.17","DOIUrl":"https://doi.org/10.1109/ICSC.2014.17","url":null,"abstract":"In this paper we propose a simple and completely automatic methodology for analyzing sentiment of users in Twitter. Firstly, we built a Twitter corpus by grouping tweets expressing positive and negative polarity through a completely automatic procedure by using only emoticons in tweets. Then, we have built a simple sentiment classifier where an actual stream of tweets from Twitter is processed and its content classified as positive, negative or neutral. The classification is made without the use of any pre-defined polarity lexicon. The lexicon is automatically inferred from the streaming of tweets. Experimental results show that our method reduces human intervention and, consequently, the cost of the whole classification process. We observe that our simple system captures polarity distinctions matching reasonably well the classification done by human judges.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122458824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Drug-drug interaction (DDI) study is an important aspect of therapy management and drug efficacy. DDI study investigates how drugs interact with each other and determine whether these interactions may lead to dire effects or nullify the therapeutic effects of each other. In this paper we model metabolic pathways of drugs that include the reaction effects between drugs and the related enzymes. By modeling the reaction effects, our model captures the degree of the effects of the interacting drugs. We introduce a novel methodology that combines semantics, ontology to model the concepts and interactions, and Answer Set Programming for temporal reasoning. We illustrate our method by inferring the effects of DDI among three drugs clozapine, olanzapine and fluvoxamine.
{"title":"Semantic Inference for Pharmacokinetic Drug-Drug Interactions","authors":"A. Moitra, R. Palla, L. Tari, M. Krishnamoorthy","doi":"10.1109/ICSC.2014.36","DOIUrl":"https://doi.org/10.1109/ICSC.2014.36","url":null,"abstract":"Drug-drug interaction (DDI) study is an important aspect of therapy management and drug efficacy. DDI study investigates how drugs interact with each other and determine whether these interactions may lead to dire effects or nullify the therapeutic effects of each other. In this paper we model metabolic pathways of drugs that include the reaction effects between drugs and the related enzymes. By modeling the reaction effects, our model captures the degree of the effects of the interacting drugs. We introduce a novel methodology that combines semantics, ontology to model the concepts and interactions, and Answer Set Programming for temporal reasoning. We illustrate our method by inferring the effects of DDI among three drugs clozapine, olanzapine and fluvoxamine.","PeriodicalId":175352,"journal":{"name":"2014 IEEE International Conference on Semantic Computing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122614082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：