To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the i...To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input text.Finally,the match was determined based on the fusion result of the two features.Experiment results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE 2.0.This Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text matching.In BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.展开更多
Role based access control is one of the widely used access control models.There are investigations in the literature that use knowledge representation mechanisms such as formal concept analysis(FCA),description logics...Role based access control is one of the widely used access control models.There are investigations in the literature that use knowledge representation mechanisms such as formal concept analysis(FCA),description logics,and Ontology for representing access control mechanism.However,while using FCA,investigations reported in the literature so far work on the logic that transforms the three dimensional access control matrix into dyadic formal contexts.This transformation is mainly to derive the formal concepts,lattice structure and implications to represent role hierarchy and constraints of RBAC.In this work,we propose a methodology that models RBAC using triadic FCA without transforming the triadic access control matrix into dyadic formal contexts.Our discussion is on two lines of inquiry.We present how triadic FCA can provide a suitable representation of RBAC policy and we demonstrate how this representation follows role hierarchy and constraints of RBAC on sample healthcare network available in the literature.展开更多
Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the d...Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the detection of HOIs is still an onerous challenge.Unlike most of the current works for HOIs detection which only rely on the pairwise information of a human and an object,we propose a graph-based HOIs detection method that models context and global structure information.Firstly,to better utilize the relations between humans and objects,the detected humans and objects are regarded as nodes to construct a fully connected undirected graph,and the graph is pruned to obtain an HOI graph that only preserving the edges connecting human and object nodes.Then,in order to obtain more robust features of human and object nodes,two different attention-based feature extraction networks are proposed,which model global and local contexts respectively.Finally,the graph attention network is introduced to pass messages between different nodes in the HOI graph iteratively,and detect the potential HOIs.Experiments on V-COCO and HICO-DET datasets verify the effectiveness of the proposed method,and show that it is superior to many existing methods.展开更多
Voltage profiles of feeders with the connection of distributed generations(DGs) were investigated.A unified typical load distribution model was established.Based on this model,exact expressions of feeder voltage profi...Voltage profiles of feeders with the connection of distributed generations(DGs) were investigated.A unified typical load distribution model was established.Based on this model,exact expressions of feeder voltage profile with single and double DGs were derived and used to analyze the impact of DG's location and capacity on the voltage profile quantitatively.Then,a general formula of the voltage profile was derived.The limitation of single DG and necessity of multiple DGs for voltage regulation were also discussed.Through the simulation,voltage profiles of feeders with single and double DGs were compared.The voltage excursion rate is 7.40% for only one DG,while 2.48% and 2.36% for double DGs.It is shown that the feeder voltage can be retained in a more appropriate range with multiple DGs than with only one DG.Distributing the total capacity of DGs is better than concentrating it at one point.展开更多
Dense captioning aims to simultaneously localize and describe regions-of-interest(RoIs)in images in natural language.Specifically,we identify three key problems:1)dense and highly overlapping RoIs,making accurate loca...Dense captioning aims to simultaneously localize and describe regions-of-interest(RoIs)in images in natural language.Specifically,we identify three key problems:1)dense and highly overlapping RoIs,making accurate localization of each target region challenging;2)some visually ambiguous target regions which are hard to recognize each of them just by appearance;3)an extremely deep image representation which is of central importance for visual recognition.To tackle these three challenges,we propose a novel end-to-end dense captioning framework consisting of a joint localization module,a contextual reasoning module and a deep convolutional neural network(CNN).We also evaluate five deep CNN structures to explore the benefits of each.Extensive experiments on visual genome(VG)dataset demonstrate the effectiveness of our approach,which compares favorably with the state-of-the-art methods.展开更多
文摘To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input text.Finally,the match was determined based on the fusion result of the two features.Experiment results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE 2.0.This Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text matching.In BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.
基金the financial support from Department of Science and Technology,Government of India under the grant:SR/CSRI/118/2014
文摘Role based access control is one of the widely used access control models.There are investigations in the literature that use knowledge representation mechanisms such as formal concept analysis(FCA),description logics,and Ontology for representing access control mechanism.However,while using FCA,investigations reported in the literature so far work on the logic that transforms the three dimensional access control matrix into dyadic formal contexts.This transformation is mainly to derive the formal concepts,lattice structure and implications to represent role hierarchy and constraints of RBAC.In this work,we propose a methodology that models RBAC using triadic FCA without transforming the triadic access control matrix into dyadic formal contexts.Our discussion is on two lines of inquiry.We present how triadic FCA can provide a suitable representation of RBAC policy and we demonstrate how this representation follows role hierarchy and constraints of RBAC on sample healthcare network available in the literature.
基金Project(51678075)supported by the National Natural Science Foundation of ChinaProject(2017GK2271)supported by the Hunan Provincial Science and Technology Department,China。
文摘Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the detection of HOIs is still an onerous challenge.Unlike most of the current works for HOIs detection which only rely on the pairwise information of a human and an object,we propose a graph-based HOIs detection method that models context and global structure information.Firstly,to better utilize the relations between humans and objects,the detected humans and objects are regarded as nodes to construct a fully connected undirected graph,and the graph is pruned to obtain an HOI graph that only preserving the edges connecting human and object nodes.Then,in order to obtain more robust features of human and object nodes,two different attention-based feature extraction networks are proposed,which model global and local contexts respectively.Finally,the graph attention network is introduced to pass messages between different nodes in the HOI graph iteratively,and detect the potential HOIs.Experiments on V-COCO and HICO-DET datasets verify the effectiveness of the proposed method,and show that it is superior to many existing methods.
基金Projects(60904101,60972164) supported by the National Natural Science Foundation of ChinaProject(N090404009) supported by the Fundamental Research Funds for the Central UniversitiesProject(20090461187) supported by China Postdoctoral Science Foundation
文摘Voltage profiles of feeders with the connection of distributed generations(DGs) were investigated.A unified typical load distribution model was established.Based on this model,exact expressions of feeder voltage profile with single and double DGs were derived and used to analyze the impact of DG's location and capacity on the voltage profile quantitatively.Then,a general formula of the voltage profile was derived.The limitation of single DG and necessity of multiple DGs for voltage regulation were also discussed.Through the simulation,voltage profiles of feeders with single and double DGs were compared.The voltage excursion rate is 7.40% for only one DG,while 2.48% and 2.36% for double DGs.It is shown that the feeder voltage can be retained in a more appropriate range with multiple DGs than with only one DG.Distributing the total capacity of DGs is better than concentrating it at one point.
基金Project(2020A1515010718)supported by the Basic and Applied Basic Research Foundation of Guangdong Province,China。
文摘Dense captioning aims to simultaneously localize and describe regions-of-interest(RoIs)in images in natural language.Specifically,we identify three key problems:1)dense and highly overlapping RoIs,making accurate localization of each target region challenging;2)some visually ambiguous target regions which are hard to recognize each of them just by appearance;3)an extremely deep image representation which is of central importance for visual recognition.To tackle these three challenges,we propose a novel end-to-end dense captioning framework consisting of a joint localization module,a contextual reasoning module and a deep convolutional neural network(CNN).We also evaluate five deep CNN structures to explore the benefits of each.Extensive experiments on visual genome(VG)dataset demonstrate the effectiveness of our approach,which compares favorably with the state-of-the-art methods.
