Knowledge Base Completion Using Embeddings and Rules
Knowledge Base Completion Using Embeddings and Rules
复制标题
DOI：
--
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Quan Wang;Bin Wang;Li Guo
中科院分区：
文献类型：
--
作者：
Quan Wang;Bin Wang;Li Guo
知识库（KB）往往是非常不完整的，需要KB完成的需求。一种有前途的方法是将知识库嵌入到潜在空间中，并通过学习和操作潜在表示来进行推理。然而，这样的嵌入模型在推理期间不使用任何规则，因此具有有限的准确性。本文提出了一种新的方法，将规则无缝地嵌入到知识库完成模型。它将推理公式化为整数线性规划（ILP）问题，目标函数由嵌入模型生成，约束条件由规则转换而来。解决ILP问题会产生许多事实，这些事实1）是嵌入模型最喜欢的，2）符合所有规则。通过引入规则，我们的方法可以大大减少解决方案的空间，并显着提高嵌入模型的推理精度。我们还提供了一个松弛技术来处理噪声的知识库，明确建模的噪声与松弛变量。两个公开的数据集上的实验结果表明，我们的方法显着，并始终优于国家的最先进的嵌入模型在KB完成。此外，松弛技术是有效的，在识别错误的事实和歧义实体，精度高于90%。
Knowledge bases (KBs) are often greatly incomplete, necessitating a demand for KB completion. A promising approach is to embed KBs into latent spaces and make inferences by learning and operating on latent representations. Such embedding models, however, do not make use of any rules during inference and hence have limited accuracy. This paper proposes a novel approach which incorporates rules seamlessly into embedding models for KB completion. It formulates inference as an integer linear programming (ILP) problem, with the objective function generated from embedding models and the constraints translated from rules. Solving the ILP problem results in a number of facts which 1) are the most preferred by the embedding models, and 2) comply with all the rules. By incorporating rules, our approach can greatly reduce the solution space and significantly improve the inference accuracy of embedding models. We further provide a slacking technique to handle noise in KBs, by explicitly modeling the noise with slack variables. Experimental results on two publicly available data sets show that our approach significantly and consistently outperforms state-of-the-art embedding models in KB completion. Moreover, the slacking technique is effective in identifying erroneous facts and ambiguous entities, with a precision higher than 90%.