基于Facet分解的知识库事实发现
Fact Discovery from Knowledge Base via Facet Decomposition
摘要:
在过去的几十年里,知识库(KBs)经历了快速的增长。然而,大多数知识库仍然存在严重的不完整性。研究人员提出了许多任务,如知识库完成和关系预测,以帮助建立知识库的表示。然而,在丰富知识库方面还有一些问题没有解决。知识库补全和关系预测假设我们知道事实三元组的两个元素,我们将预测缺失的一个。这一假设在实践中受到太多的限制,妨碍了它直接发现新的事实。为了解决这个问题,我们提出了一个新的任务,即从知识库中发现事实。这个任务只需要我们知道头部实体,目标是发现与头部实体相关的事实。为了解决这个新问题,我们提出了一个新的框架,分解成几个方面发现组件的发现问题。我们还提出了一种新的自动编码器为基础的方面的组成部分,估计一些方面的事实。此外,我们提出了一个反馈学习组件,以共享每个方面之间的信息。我们使用基准数据集评估我们的框架,实验结果表明,我们的框架取得了可喜的成果。我们还对我们的框架进行了广泛的分析,以发现不同种类的事实。本文的源代码可以从https://github.com/thunlp/FFD获得。
英文摘要:
During the past few decades, knowledge bases (KBs) have experienced rapid growth. Nevertheless, most KBs still suffer from serious incompletion. Researchers proposed many tasks such as knowledge base completion and relation prediction to help build the representation of KBs. However, there are some issues unsettled towards enriching the KBs. Knowledge base completion and relation prediction assume that we know two elements of the fact triples and we are going to predict the missing one. This assumption is too restricted in practice and prevents it from discovering new facts directly. To address this issue, we propose a new task, namely, fact discovery from knowledge base. This task only requires that we know the head entity and the goal is to discover facts associated with the head entity. To tackle this new problem, we propose a novel framework that decomposes the discovery problem into several facet discovery components. We also propose a novel auto-encoder based facet component to estimate some facets of the fact. Besides, we propose a feedback learning component to share the information between each facet. We evaluate our framework using a benchmark dataset and the experimental results show that our framework achieves promising results. We also conduct extensive analysis of our framework in discovering different kinds of facts. The source code of this paper can be obtained from https://github.com/thunlp/FFD.
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。