arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.04509cs.AIcs.DBcs.LGstat.ML
收藏

IterefinE:使用符号知识的迭代KG精化嵌入

IterefinE: Iterative KG Refinement Embeddings using Symbolic Knowledge

Siddhant Arora, Srikanta Bedathur, Maya Ramanath, Deepak Sharma

摘要:

从文本源中提取的知识图(Knowledge Graph,KG)往往带有噪声,导致下游应用任务(如基于KG的问答)的性能不佳。虽然最近的许多活动都集中在通过使用嵌入来推断新事实来解决KG的稀疏性,但通过KG精化任务来清除KG中的噪声的问题并没有得到积极的研究。大多数成功的KG细化技术利用推理规则和本体推理。除了少数例外,嵌入不利用本体信息,并且它们在KG细化任务中的表现还没有得到很好的理解。在本文中,我们提出了一个KG细化框架称为IterefinE迭代结合两种技术-一个使用本体信息和推理规则,PSL-KGI,和KG嵌入,如ComplEx和ConvE不。因此,IterefinE不仅能够利用本体信息来提高预测的质量,而且还能够利用KG嵌入的能力(隐式地)执行更长的推理链。IterefinE框架在协同训练模式下运行,并导致从PSL-KGI(我们称之为TypeE-X)中细化的KG的显式类型监督嵌入。我们在一系列KG基准上的实验表明,我们产生的嵌入能够拒绝KG中的噪声事实,同时推断出更高质量的新事实,从而使整体加权F1得分提高了9%

英文摘要:

Knowledge Graphs (KGs) extracted from text sources are often noisy and lead to poor performance in downstream application tasks such as KG-based question answering.While much of the recent activity is focused on addressing the sparsity of KGs by using embeddings for inferring new facts, the issue of cleaning up of noise in KGs through KG refinement task is not as actively studied. Most successful techniques for KG refinement make use of inference rules and reasoning over ontologies. Barring a few exceptions, embeddings do not make use of ontological information, and their performance in KG refinement task is not well understood. In this paper, we present a KG refinement framework called IterefinE which iteratively combines the two techniques - one which uses ontological information and inferences rules, PSL-KGI, and the KG embeddings such as ComplEx and ConvE which do not. As a result, IterefinE is able to exploit not only the ontological information to improve the quality of predictions, but also the power of KG embeddings which (implicitly) perform longer chains of reasoning. The IterefinE framework, operates in a co-training mode and results in explicit type-supervised embedding of the refined KG from PSL-KGI which we call as TypeE-X. Our experiments over a range of KG benchmarks show that the embeddings that we produce are able to reject noisy facts from KG and at the same time infer higher quality new facts resulting in up to 9% improvement of overall weighted F1 score

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。

↑