arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00418cs.AIcs.DBcs.LGcs.LO
收藏

面向复杂查询的逻辑嵌入

Logic Embeddings for Complex Query Answering

IBM Research(IBM研究院)

Francois Luus, Prithviraj Sen, Pavan Kapanipathi, Ryan Riegel, Ndivhuwo Makondo, Thabang Lebese, Alexander Gray

摘要:

在不完整的知识库上进行逻辑查询是具有挑战性的,因为:1)它要求隐式链接预测,以及2)存在一阶逻辑查询的蛮力应答在存在变量的数量上是指数的。近年来的查询嵌入方法提供了快速查询的能力,但大多数方法都是用封闭区域来建模集合逻辑,缺乏否定性。支持否定的查询嵌入使用的密度存在缺点:1)只能即兴发挥逻辑,2)使用昂贵的分布,3)对答案的不确定性建模不佳。在本文中,我们提出了逻辑嵌入,一种新的方法来嵌入复杂的查询,使用Skolemisation消除存在的变量进行有效的查询。它支持否定,但改进了密度方法:1)集成了研究良好的t-范数逻辑并直接评估可满足性,2)简化了真值建模,3)用真值界建模不确定性。逻辑嵌入在对大的、不完整的知识图谱的查询应答中具有竞争力的快速和准确性,在否定查询上优于否定查询,并且特别地,提供了对答案不确定性的改进的建模,如答案集大小和嵌入熵之间的优越相关性所证明的。

英文摘要:

Answering logical queries over incomplete knowledge bases is challenging because: 1) it calls for implicit link prediction, and 2) brute force answering of existential first-order logic queries is exponential in the number of existential variables. Recent work of query embeddings provides fast querying, but most approaches model set logic with closed regions, so lack negation. Query embeddings that do support negation use densities that suffer drawbacks: 1) only improvise logic, 2) use expensive distributions, and 3) poorly model answer uncertainty. In this paper, we propose Logic Embeddings, a new approach to embedding complex queries that uses Skolemisation to eliminate existential variables for efficient querying. It supports negation, but improves on density approaches: 1) integrates well-studied t-norm logic and directly evaluates satisfiability, 2) simplifies modeling with truth values, and 3) models uncertainty with truth bounds. Logic Embeddings are competitively fast and accurate in query answering over large, incomplete knowledge graphs, outperform on negation queries, and in particular, provide improved modeling of answer uncertainty as evidenced by a superior correlation between answer set size and embedding entropy.

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。

↑