Effective emergency management relies on timely risk identification and decision-making,wherein natural language processing plays a vital role.Hyper-relational knowledge graph(HKG)representation,which embeds entities ...Effective emergency management relies on timely risk identification and decision-making,wherein natural language processing plays a vital role.Hyper-relational knowledge graph(HKG)representation,which embeds entities and their complex relations into latent space,provides a strong foundation for supporting emergency responses.Existing methods consider either inter-entity or inter-fact dependencies,leading to the loss of interaction information at the unconsidered level(fact level or entity level).To address the above issue,we propose a position-aware attention model based on dual-level contrastive learning(PDCL)for HKG representation.First,the complete and co-occurrence graphs were constructed and encoded using different graph convolutional networks,generating different embedding views for entities and facts.Second,entity-level and fact-level contrastive objectives were designed to enhance information exchange between the two levels in a self-supervised manner.Finally,a linear transformation corresponding to the ordinal information of each element was used to integrate positional constraints into the representation of the HKG.Experimental results for three benchmark datasets showed that the PDCL model outperformed existing state-of-the-art methods.Especially,MRR and Hits@1 values could be improved by up to 1.8%and 3.3%,respectively.展开更多
The Knowledge Graph(KGs)have profoundly impacted many researchfields.However,there is a problem of low data integrity in KGs.The binary-relational knowledge graph is more common in KGs but is limited by less informatio...The Knowledge Graph(KGs)have profoundly impacted many researchfields.However,there is a problem of low data integrity in KGs.The binary-relational knowledge graph is more common in KGs but is limited by less information.It often has less content to use when predicting missing entities(relations).The hyper-relational knowledge graph is another form of KGs,which introduces much additional information(qualifiers)based on the main triple.The hyper-relational knowledge graph can effectively improve the accuracy of pre-dicting missing entities(relations).The existing hyper-relational link prediction methods only consider the overall perspective when dealing with qualifiers and calculate the score function by combining the qualifiers with the main triple.How-ever,these methods overlook the inherent characteristics of entities and relations.This paper proposes a novel Local and Global Hyper-relation Aggregation Embed-ding for Link Prediction(LGHAE).LGHAE can capture the semantic features of hyper-relational data from local and global perspectives.To fully utilize local and global features,Hyper-InteractE,as a new decoder,is designed to predict missing entities to fully utilize local and global features.We validated the feasibility of LGHAE by comparing it with state-of-the-art models on public datasets.展开更多
基金supported in part by the National Key Research and Development Program of China under the grant No.2021YFC3300602the Outstanding Academic Leader Project of Shanghai under the grant No.20XD1401700the National Natural Science Foundation of China under the grant No.91746203.
文摘Effective emergency management relies on timely risk identification and decision-making,wherein natural language processing plays a vital role.Hyper-relational knowledge graph(HKG)representation,which embeds entities and their complex relations into latent space,provides a strong foundation for supporting emergency responses.Existing methods consider either inter-entity or inter-fact dependencies,leading to the loss of interaction information at the unconsidered level(fact level or entity level).To address the above issue,we propose a position-aware attention model based on dual-level contrastive learning(PDCL)for HKG representation.First,the complete and co-occurrence graphs were constructed and encoded using different graph convolutional networks,generating different embedding views for entities and facts.Second,entity-level and fact-level contrastive objectives were designed to enhance information exchange between the two levels in a self-supervised manner.Finally,a linear transformation corresponding to the ordinal information of each element was used to integrate positional constraints into the representation of the HKG.Experimental results for three benchmark datasets showed that the PDCL model outperformed existing state-of-the-art methods.Especially,MRR and Hits@1 values could be improved by up to 1.8%and 3.3%,respectively.
文摘The Knowledge Graph(KGs)have profoundly impacted many researchfields.However,there is a problem of low data integrity in KGs.The binary-relational knowledge graph is more common in KGs but is limited by less information.It often has less content to use when predicting missing entities(relations).The hyper-relational knowledge graph is another form of KGs,which introduces much additional information(qualifiers)based on the main triple.The hyper-relational knowledge graph can effectively improve the accuracy of pre-dicting missing entities(relations).The existing hyper-relational link prediction methods only consider the overall perspective when dealing with qualifiers and calculate the score function by combining the qualifiers with the main triple.How-ever,these methods overlook the inherent characteristics of entities and relations.This paper proposes a novel Local and Global Hyper-relation Aggregation Embed-ding for Link Prediction(LGHAE).LGHAE can capture the semantic features of hyper-relational data from local and global perspectives.To fully utilize local and global features,Hyper-InteractE,as a new decoder,is designed to predict missing entities to fully utilize local and global features.We validated the feasibility of LGHAE by comparing it with state-of-the-art models on public datasets.
