2015/05/10 by Miao Fan, Qiang Zhou, Fan, Miao +7
Computer Science · Decision Sciences · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Data Quality and Management #FOS: Computer and information sciences #Topic Modeling #cs.AI
paper · pdf · doi:10.48550/arxiv.1505.02433
arXiv admin note: text overlap with arXiv:1503.08155
openalex publication_date 2015/05/10 · arxiv created 2015/05/22 · arxiv updated 2015/05/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper contributes a novel embedding model which measures the probability of each belief ⟨ h,r,t,m⟩ in a large-scale knowledge repository via simultaneously learning distributed representations for entities (h and t), relations (r), and the words in relation mentions (m). It facilitates knowledge completion by means of simple vector operations to discover new beliefs. Given an imperfect belief, we can not only infer the missing entities, predict the unknown relations, but also tell the plausibility of the belief, just leveraging the learnt embeddings of remaining evidences. To demonstrate the scalability and the effectiveness of our model, we conduct experiments on several large-scale repositories which contain millions of beliefs from WordNet, Freebase and NELL, and compare it with other cutting-edge approaches via competing the performances assessed by the tasks of entity inference, relation prediction and triplet classification with respective metrics. Extensive experimental results show that the proposed model outperforms the state-of-the-arts with significant improvements.