In contrast with the research of new models,little attention has been paid to the impact of low or high-quality data feeding a dialogue system.The present paper makes thefirst attempt tofill this gap by extending our ...In contrast with the research of new models,little attention has been paid to the impact of low or high-quality data feeding a dialogue system.The present paper makes thefirst attempt tofill this gap by extending our previous work on question-answering(QA)systems by investigating the effect of misspelling on QA agents and how context changes can enhance the responses.Instead of using large language models trained on huge datasets,we propose a method that enhances the model's score by modifying only the quality and structure of the data feed to the model.It is important to identify the features that modify the agent performance because a high rate of wrong answers can make the students lose their interest in using the QA agent as an additional tool for distant learning.The results demonstrate the accuracy of the proposed context simplification exceeds 85%.Thesefindings shed light on the importance of question data quality and context complexity construct as key dimensions of the QA system.In conclusion,the experimental results on questions and contexts showed that controlling and improving the various aspects of data quality around the QA system can significantly enhance his robustness and performance.展开更多
A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorit...A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorithm for discretizing continuous numeric-values is brought forth to reshape these QoS metrics and contexts into their discrete forms. For QoS qualitative diagnosis, causal relationships between a QoS metric and its contexts are exploited with K2 Bayesian network （BN） structure learning by treating QoS metrics and contexts as BN nodes. A QoS metric node is qualitatively diagnosed to be causally related to its parent context nodes. To guarantee QoS quantitatively, those causal relationships are next modeled quantitatively by BN parameter learning. Then, BN inference can be carried out on the BN. Finally, the QoS metric is guaranteed to a specific value with certain probability by tuning its causal contexts to suitable values suggested by the BN inference. Our approach is validated to be sound and effective by simulations on a peer-to-peer （P2P） network.展开更多
Mobility support for the next generation IPv6 networks has been one of the recent research issues due to the growing demand for wireless services over internet.In the other hand,3GPP has introduced IP Multimedia Subsy...Mobility support for the next generation IPv6 networks has been one of the recent research issues due to the growing demand for wireless services over internet.In the other hand,3GPP has introduced IP Multimedia Subsystem as the next generation IP based infrastructure for wireless and wired multimedia services.In this paper we present two context transfer mechanisms based on predictive and reactive schemes,to support seamless handover in IMS over Mobile IPv6.Those schemes reduce handover latency by transferring appropriate session information between the old and the new access networks.Moreover,we present two methods for QoS parameters negotiations to preserve service quality along the mobile user movement path.The performances of the proposed mechanisms are evaluated by simulations.展开更多
文摘In contrast with the research of new models,little attention has been paid to the impact of low or high-quality data feeding a dialogue system.The present paper makes thefirst attempt tofill this gap by extending our previous work on question-answering(QA)systems by investigating the effect of misspelling on QA agents and how context changes can enhance the responses.Instead of using large language models trained on huge datasets,we propose a method that enhances the model's score by modifying only the quality and structure of the data feed to the model.It is important to identify the features that modify the agent performance because a high rate of wrong answers can make the students lose their interest in using the QA agent as an additional tool for distant learning.The results demonstrate the accuracy of the proposed context simplification exceeds 85%.Thesefindings shed light on the importance of question data quality and context complexity construct as key dimensions of the QA system.In conclusion,the experimental results on questions and contexts showed that controlling and improving the various aspects of data quality around the QA system can significantly enhance his robustness and performance.
基金Supported by the National High Technology Research and Development Program of China （No. 2007AA010302, 2009AA012404） the National Basic Research Program of China （No. 2007CB307103）+1 种基金 the National Natural Science Foundation of China （No. 60432010, 60802034） the Specialized Research Fund for the Doctoral Program of Higher Education （No. 20070013026）.
文摘A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorithm for discretizing continuous numeric-values is brought forth to reshape these QoS metrics and contexts into their discrete forms. For QoS qualitative diagnosis, causal relationships between a QoS metric and its contexts are exploited with K2 Bayesian network （BN） structure learning by treating QoS metrics and contexts as BN nodes. A QoS metric node is qualitatively diagnosed to be causally related to its parent context nodes. To guarantee QoS quantitatively, those causal relationships are next modeled quantitatively by BN parameter learning. Then, BN inference can be carried out on the BN. Finally, the QoS metric is guaranteed to a specific value with certain probability by tuning its causal contexts to suitable values suggested by the BN inference. Our approach is validated to be sound and effective by simulations on a peer-to-peer （P2P） network.
文摘Mobility support for the next generation IPv6 networks has been one of the recent research issues due to the growing demand for wireless services over internet.In the other hand,3GPP has introduced IP Multimedia Subsystem as the next generation IP based infrastructure for wireless and wired multimedia services.In this paper we present two context transfer mechanisms based on predictive and reactive schemes,to support seamless handover in IMS over Mobile IPv6.Those schemes reduce handover latency by transferring appropriate session information between the old and the new access networks.Moreover,we present two methods for QoS parameters negotiations to preserve service quality along the mobile user movement path.The performances of the proposed mechanisms are evaluated by simulations.
