Probabilistic Belief Embedding for Knowledge Base Completion
This work addresses the problem of completing and verifying beliefs in large knowledge bases for applications in AI and data mining, representing an incremental advancement over existing embedding methods.
The paper tackles knowledge base completion by introducing a probabilistic belief embedding model that learns distributed representations for entities, relations, and relation mentions to infer missing entities, predict unknown relations, and assess belief plausibility. It demonstrates significant improvements over state-of-the-art methods on large-scale repositories like WordNet, Freebase, and NELL.
This paper contributes a novel embedding model which measures the probability of each belief $\langle h,r,t,m\rangle$ 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.