Multi-Task Learning and Improved TextRank for Knowledge Graph Completion

• Published in: Entropy (Basel, Switzerland) Vol. 24; no. 10; p. 1495
• Main Authors: Tian, Hao, Zhang, Xiaoxiong, Wang, Yuhan, Zeng, Daojian
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 20.10.2022; MDPI
• Subjects: a lite bidirectional encoder representations from transformers (ALBERT); Algorithms; Coders; Computational linguistics; Datasets; Efficiency; extractive summarization; Keywords; Knowledge; knowledge completion; Knowledge representation; Language; Language processing; Learning; Methods; multi-task learning; Natural language interfaces; Neural networks; Ontology; Rankings; Resource Description Framework-RDF; Semantic web; Semantics; a lite bidirectional encoder representations from transformers (ALBERT); multi-task learning; extractive summarization; knowledge completion
• ISSN: 1099-4300; 1099-4300
• DOI: 10.3390/e24101495

Knowledge graph completion is an important technology for supplementing knowledge graphs and improving data quality. However, the existing knowledge graph completion methods ignore the features of triple relations, and the introduced entity description texts are long and redundant. To address these problems, this study proposes a multi-task learning and improved TextRank for knowledge graph completion (MIT-KGC) model. The key contexts are first extracted from redundant entity descriptions using the improved TextRank algorithm. Then, a lite bidirectional encoder representations from transformers (ALBERT) is used as the text encoder to reduce the parameters of the model. Subsequently, the multi-task learning method is utilized to fine-tune the model by effectively integrating the entity and relation features. Based on the datasets of WN18RR, FB15k-237, and DBpedia50k, experiments were conducted with the proposed model and the results showed that, compared with traditional methods, the mean rank (MR), top 10 hit ratio (Hit@10), and top three hit ratio (Hit@3) were enhanced by 38, 1.3%, and 1.9%, respectively, on WN18RR. Additionally, the MR and Hit@10 were increased by 23 and 0.7%, respectively, on FB15k-237. The model also improved the Hit@3 and the top one hit ratio (Hit@1) by 3.1% and 1.5% on the dataset DBpedia50k, respectively, verifying the validity of the model.