arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.15643cs.AIcs.CL
收藏

通过复杂逻辑假设生成推进知识图谱中的溯因推理

Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation

Hong Kong University of Science and Technology(香港科技大学);Amazon.com Inc(亚马逊公司)

Jiaxin Bai, Yicheng Wang, Tianshi Zheng, Yue Guo, Xin Liu, Yangqiu Song

AI总结:

针对知识图谱中溯因推理研究不足的问题,提出复杂逻辑假设生成任务及RLF-KG方法,提升假设解释效果并在三个常用知识图谱上取得最优结果。

摘要:

溯因推理是做出有依据的猜测以对观测结果提供解释的过程。尽管众多应用需要运用知识来开展解释,但溯因推理与知识图谱这类结构化知识结合的使用仍在很大程度上未被探究。为填补这一空白,本文提出了复杂逻辑假设生成任务,作为实现知识图谱(KG)溯因逻辑推理的初步步骤。该任务的目标是生成一个复杂逻辑假设,使其能够解释一组观测结果。我们发现,经监督训练的生成模型可以生成在结构上更接近参考假设的逻辑假设。然而,当泛化到未见过的观测结果时,这种训练目标无法保证生成更优的假设。为解决这一问题,我们提出了知识图谱强化学习(RLF-KG)方法,该方法最小化观测结果与根据知识图谱从生成假设推导得出的结论之间的差异。实验表明,在RLF-KG的助力下,生成的假设能提供更优的解释,并且在三个广泛使用的知识图谱上取得了当前最优(state-of-the-art)结果。

英文摘要:

Abductive reasoning is the process of making educated guesses to provide explanations for observations. Although many applications require the use of knowledge for explanations, the utilization of abductive reasoning in conjunction with structured knowledge, such as a knowledge graph, remains largely unexplored. To fill this gap, this paper introduces the task of complex logical hypothesis generation, as an initial step towards abductive logical reasoning with KG. In this task, we aim to generate a complex logical hypothesis so that it can explain a set of observations. We find that the supervised trained generative model can generate logical hypotheses that are structurally closer to the reference hypothesis. However, when generalized to unseen observations, this training objective does not guarantee better hypothesis generation. To address this, we introduce the Reinforcement Learning from Knowledge Graph (RLF-KG) method, which minimizes differences between observations and conclusions drawn from generated hypotheses according to the KG. Experiments show that, with RLF-KG's assistance, the generated hypotheses provide better explanations, and achieve state-of-the-art results on three widely used KGs.

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。

↑