Skip to main content

Table 2 Comparison of various research models

From: Multi-source knowledge fusion: a survey

ModelFused Information TypesVerification task
Zhong et al. (20,150 [29]text descriptions of entitiesLink prediction, Triplet classification, Relational fact extraction, and Analogical reasoning
SEEA [32]Semantical Information of Attributes of EntitiesEntity aligment
TADW [33]Text features of verticesMulti-class classification of vertices
CANE [34]Structure –based information, Text-based context informationLink prediction, Vertex classification
CKE [35]Structural knowledge, Textual knowledge and visual knowledge, The information of users and itemsMovie and book recommendation
DKRL [39]semantic of entity descriptionsKG completion entity classification (in Zero-shot Scenario)
TransC [43]Differentiating concepts and instance in entitiesLink prediction, Triple classification
KALE [43]Jointly embedding KGs and logical rulesLink prediction, Triple classification
Rocktaschel et al. (2015) [45]Logical Background KnowledgeRelation Extraction
Newman-Griffis et al. (2018) [46]Entities and surfaces forms, Text informationAnalogy completion, Entity sense disambiguation
SSE [47]Additional Semantic information (Semantically Smooth Embedding)Link prediction, Triple classification
TKRL [48]Hierarchical entity type informationKG completion, Triple classification
Jointly (A-LSTM) [49]Both structural and textual information of entitiesLink prediction, Triple classification
TEKE [50]Textual context information (Text-enchanced knowledge embedding)Link prediction, Triple classification (Capability to handle 1-to-N, N-to 1, N-to-N relations, and KG spareseness)