Multilingual Knowledge Graph Completion Based on Structure Features of the Dual-Branch

With the development of information fusion, knowledge graph completion tasks have received a lot of attention.​ some studies investigate the broader underlying problems of linguistics, while embedding learning has a narrow focus.​This poses significant challenges due to the heterogeneity of coarse-graining patterns. Then, to settle the whole matter,​ a framework for completion is designed, named Triple Encoder-Scoring Module (TEsm). The model employs an alternating two-branch structure that fuses local features into the interaction pattern of the triplet itself by perfectly combining distance and structure models. Moreover, it is mapped to a uniform shared space. Upon completion, an ensemble inference method is proposed to query multiple predictions from different graphs using a weight classifier. Experiments show that the experimental dataset used for the completion task is DBpedia, which contains five different linguistic subsets..​Our extensive experimental results demonstrate that TEsm can efficiently and smoothly solve the optimal completion task, validating the performance of the proposed model.