Since extracting structured information with automatic annotation,distantly supervised relation extraction(DSRE)reduces the cost of labor greatly and has become a remarkable approach to relation extraction.However,DSR...Since extracting structured information with automatic annotation,distantly supervised relation extraction(DSRE)reduces the cost of labor greatly and has become a remarkable approach to relation extraction.However,DSRE also produces a lot of mislabeled data in automatic annotation.To address this issue,this paper proposes a novel DSRE model,based on collaborative encoders with hierarchy relation of relations,namely CEH-RORs.In particular,CEH-RORs proposes collaborative encoders,which not only dynamically control the amount of information but also select useful information as effectively as possible.Moreover,this paper constructs the hierarchical graph based on the graph attention network(GAT)to aggregate the node information,in which each relation in the hierarchy of relations forms a node in the input graph.In addition,this paper further improves the performance by using pre-trained relational embeddings.Extensive experiments demonstrate that our approach improved AUC by 4.69%and average P@N to 1.78%compared to its sub-optimal value of existing remarkable models.展开更多
A relative embedding of a connected graph is an embedding of the graph in some surface with respect to some closed walks, each of which bounds a face of the embedding. The relative maximum genus of a connected graph i...A relative embedding of a connected graph is an embedding of the graph in some surface with respect to some closed walks, each of which bounds a face of the embedding. The relative maximum genus of a connected graph is the maximum of integer k with the property that the graph has a relative embedding in the orientable surface with k handles. A polynomial algorithm is provided for constructing relative maximum genus embedding of a graph of the relative tree of the graph is planar. Under this condition, just like maximum genus embedding, a graph does not have any locally strict maximum genus.展开更多
基金supported by the IFLYtek University Wisdom Teaching Innovation Research Project based on the 2022 Industry-University-Research Innovation Fund of China University(No.2022 XF 016).
文摘Since extracting structured information with automatic annotation,distantly supervised relation extraction(DSRE)reduces the cost of labor greatly and has become a remarkable approach to relation extraction.However,DSRE also produces a lot of mislabeled data in automatic annotation.To address this issue,this paper proposes a novel DSRE model,based on collaborative encoders with hierarchy relation of relations,namely CEH-RORs.In particular,CEH-RORs proposes collaborative encoders,which not only dynamically control the amount of information but also select useful information as effectively as possible.Moreover,this paper constructs the hierarchical graph based on the graph attention network(GAT)to aggregate the node information,in which each relation in the hierarchy of relations forms a node in the input graph.In addition,this paper further improves the performance by using pre-trained relational embeddings.Extensive experiments demonstrate that our approach improved AUC by 4.69%and average P@N to 1.78%compared to its sub-optimal value of existing remarkable models.
文摘A relative embedding of a connected graph is an embedding of the graph in some surface with respect to some closed walks, each of which bounds a face of the embedding. The relative maximum genus of a connected graph is the maximum of integer k with the property that the graph has a relative embedding in the orientable surface with k handles. A polynomial algorithm is provided for constructing relative maximum genus embedding of a graph of the relative tree of the graph is planar. Under this condition, just like maximum genus embedding, a graph does not have any locally strict maximum genus.
