arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1505.02433cs.AI
收藏

知识库完备的概率信念嵌入

Probabilistic Belief Embedding for Knowledge Base Completion

Tsinghua University(清华大学);University of Stirling(斯特灵大学);New York University(纽约大学)

Miao Fan, Qiang Zhou, Andrew Abel, Thomas Fang Zheng, Ralph Grishman

摘要:

本文提出了一种新的嵌入模型,该模型通过同时学习实体($h$和$t$)、关系($r$)和关系提及中的词($m$)的分布式表示来度量大规模知识库中每个信念$\langle h,r,t,m\rangle$的概率。它通过简单的向量操作来发现新的信念,从而促进知识的完成。给定一个不完美的信念,我们不仅可以推断出缺失的实体,预测未知的关系,而且还告诉信念的可信性,只是利用剩余证据的学习嵌入。为了证明我们的模型的可扩展性和有效性,我们在几个包含来自WordNet,Freebase和NELL的数百万个信念的大型存储库上进行实验,并将其与其他尖端方法进行比较,通过竞争实体推理,关系预测和三元组分类任务评估的性能。大量的实验结果表明,该模型优于国家的最先进的显着改善。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑