Relational similarity measurement as a popular research area in the field of natural language processing, is widely used in information retrieval, word sense disambiguation, machine translation and so on. The existing approaches are mostly based on extracting semantic features as feature matrixes from the large-scale corpus and using the corresponding method to process these feature matrixes to compute the relational similarity between word-pairs. However, the extracted semantic features are loosely distributed, which make the sparseness of feature matrixes. This paper proposes a Multi-Task Lasso based Relational similarity measure method (MTLRel), which makes snippets retrieved from a web search engine as the semantic information sources of a word-pair, then builds the feature matrix by extracting predefined patterns from snippets, compress and denoise the feature matrix into a feature vector using a multi-task lasso method, finally measures the relational similarity between two word-pairs by computing the cosine of the angle between two feature vectors. The MTLRel approach achieves an accuracy rate of 50.3% by testing 374 SAT analogy questions with lower time consumption.
{"title":"Relational Similarity Measurement between Word-pairs Using Multi-Task Lasso","authors":"Dongbin Yan, Zhao Lu","doi":"10.1109/CSC.2012.35","DOIUrl":"https://doi.org/10.1109/CSC.2012.35","url":null,"abstract":"Relational similarity measurement as a popular research area in the field of natural language processing, is widely used in information retrieval, word sense disambiguation, machine translation and so on. The existing approaches are mostly based on extracting semantic features as feature matrixes from the large-scale corpus and using the corresponding method to process these feature matrixes to compute the relational similarity between word-pairs. However, the extracted semantic features are loosely distributed, which make the sparseness of feature matrixes. This paper proposes a Multi-Task Lasso based Relational similarity measure method (MTLRel), which makes snippets retrieved from a web search engine as the semantic information sources of a word-pair, then builds the feature matrix by extracting predefined patterns from snippets, compress and denoise the feature matrix into a feature vector using a multi-task lasso method, finally measures the relational similarity between two word-pairs by computing the cosine of the angle between two feature vectors. The MTLRel approach achieves an accuracy rate of 50.3% by testing 374 SAT analogy questions with lower time consumption.","PeriodicalId":183800,"journal":{"name":"2012 International Conference on Cloud and Service Computing","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129532069","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}
As the pillar of the service oriented architecture in exposing business activities in a highly standardized manner, Web services have emerged as the promising solution to do business more efficiently, and to adapt to ever more changing needs and competitions. Therefore the number of Web services has substantially increased in response to the highly increased needs of businesses and companies. However, to bind to relevant Web services, users need to browse separately a huge number of business registries which consumes time and effort. To cope with this challenge and in response to limits of existing solutions, we propose a local repository-based approach that optimizes the binding of Web services of interest. Furthermore, we present experimental results situating the proposed approach to other ones dealing with the same issue.
{"title":"Binding Web Services: An Optimizing Approach","authors":"Jaber Kouki, Walid Chainbi, K. Ghédira","doi":"10.1109/CSC.2012.18","DOIUrl":"https://doi.org/10.1109/CSC.2012.18","url":null,"abstract":"As the pillar of the service oriented architecture in exposing business activities in a highly standardized manner, Web services have emerged as the promising solution to do business more efficiently, and to adapt to ever more changing needs and competitions. Therefore the number of Web services has substantially increased in response to the highly increased needs of businesses and companies. However, to bind to relevant Web services, users need to browse separately a huge number of business registries which consumes time and effort. To cope with this challenge and in response to limits of existing solutions, we propose a local repository-based approach that optimizes the binding of Web services of interest. Furthermore, we present experimental results situating the proposed approach to other ones dealing with the same issue.","PeriodicalId":183800,"journal":{"name":"2012 International Conference on Cloud and Service Computing","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132240372","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}
Although some cloud providers look at the hybrid cloud as blasphemy, there are strong reasons for them to adopt it. Hybrid clouds offer the cost and scale benefits of public clouds while also offering the security and control of private clouds. Task scheduling, one of the most famous combinational optimization problems, plays a key role in the hybrid cloud environment. We propose a graph-based task scheduling algorithm. In order to achieve minimum cost, our algorithm takes into account not only the private resources but also the public resources. This paper also presents an extensive evaluation study and demonstrates that our proposed algorithms minimize the user's cost in a hybrid cloud environment.
{"title":"A New Task Scheduling Algorithm in Hybrid Cloud Environment","authors":"W. Jiang, Z. Sheng","doi":"10.1109/CSC.2012.15","DOIUrl":"https://doi.org/10.1109/CSC.2012.15","url":null,"abstract":"Although some cloud providers look at the hybrid cloud as blasphemy, there are strong reasons for them to adopt it. Hybrid clouds offer the cost and scale benefits of public clouds while also offering the security and control of private clouds. Task scheduling, one of the most famous combinational optimization problems, plays a key role in the hybrid cloud environment. We propose a graph-based task scheduling algorithm. In order to achieve minimum cost, our algorithm takes into account not only the private resources but also the public resources. This paper also presents an extensive evaluation study and demonstrates that our proposed algorithms minimize the user's cost in a hybrid cloud environment.","PeriodicalId":183800,"journal":{"name":"2012 International Conference on Cloud and Service Computing","volume":" 82","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113952582","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}
The growth of the Semantic Web has seen a rapid increase in the amount of Resource Description Framework (RDF) data. Meanwhile, the demand for access to RDF data without detailed knowledge of RDF query languages is increasing. In this study, an approach enabling keyword-based semantic information query over RDF data is proposed. The approach sets up a keyword-inverted index and a relation index based on the r-radius+ graph and searches the connecting nodes to provide an answer for keyword query. Moreover, the approach uses an improved scoring function based on textual relevancy and relation popularity and supports top-k queries. Experimental results show that the proposed approach can achieve good query performance.
{"title":"An Approach to Semantic Information Retrieval","authors":"Huiying Li","doi":"10.1109/CSC.2012.32","DOIUrl":"https://doi.org/10.1109/CSC.2012.32","url":null,"abstract":"The growth of the Semantic Web has seen a rapid increase in the amount of Resource Description Framework (RDF) data. Meanwhile, the demand for access to RDF data without detailed knowledge of RDF query languages is increasing. In this study, an approach enabling keyword-based semantic information query over RDF data is proposed. The approach sets up a keyword-inverted index and a relation index based on the r-radius+ graph and searches the connecting nodes to provide an answer for keyword query. Moreover, the approach uses an improved scoring function based on textual relevancy and relation popularity and supports top-k queries. Experimental results show that the proposed approach can achieve good query performance.","PeriodicalId":183800,"journal":{"name":"2012 International Conference on Cloud and Service Computing","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126230265","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}
The existing Internet traffic passive measurement solutions are mainly based on a technical route of downloading traffic dataset and analysis tool from the corresponding distribution site, and then carrying out a local place research based on off-line traffic analysis. However, the issues of massive traffic datasets acquisition and analysis as well as measurement achievement reuse and sharing still need a further consideration. The paper applies the ever up surging cloud computing paradigm to network traffic passive measurement field in order to address the issues. On the basis of inducing the drawbacks of the conventional technical route, we proposed a novel cloud pattern of passive measurement work and designed an architecture of cloud-pattern based network traffic analysis platform. Furthermore, using the authentic traffic collected at a CERNET backbone (10 Gbps), we implemented a prototype system of the architecture, called IP Trace Analysis System, or IPTAS for short. Combined with IPTAS, the paper elaborates the critical implementations of the architecture and verifies its feasibility and flexibility through IPTAS application instances.
{"title":"A Cloud-Pattern Based Network Traffic Analysis Platform for Passive Measurement","authors":"Heng Wang, W. Ding, Zhen Xia","doi":"10.1109/CSC.2012.8","DOIUrl":"https://doi.org/10.1109/CSC.2012.8","url":null,"abstract":"The existing Internet traffic passive measurement solutions are mainly based on a technical route of downloading traffic dataset and analysis tool from the corresponding distribution site, and then carrying out a local place research based on off-line traffic analysis. However, the issues of massive traffic datasets acquisition and analysis as well as measurement achievement reuse and sharing still need a further consideration. The paper applies the ever up surging cloud computing paradigm to network traffic passive measurement field in order to address the issues. On the basis of inducing the drawbacks of the conventional technical route, we proposed a novel cloud pattern of passive measurement work and designed an architecture of cloud-pattern based network traffic analysis platform. Furthermore, using the authentic traffic collected at a CERNET backbone (10 Gbps), we implemented a prototype system of the architecture, called IP Trace Analysis System, or IPTAS for short. Combined with IPTAS, the paper elaborates the critical implementations of the architecture and verifies its feasibility and flexibility through IPTAS application instances.","PeriodicalId":183800,"journal":{"name":"2012 International Conference on Cloud and Service Computing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133503982","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：