不完全和不完全知识库上知识推理的嵌入表示学习
Learning Embedding Representations for Knowledge Inference on Imperfect and Incomplete Repositories
摘要：
本文首次尝试通过嵌入实体和关系的方法，研究了不完全覆盖的大规模不完全知识库的知识推理问题。我们建议IIKE（不完全和不完整的知识嵌入），一种概率模型，其测量在诸如NELL和Freebase的大规模知识库中的每个信念的概率，即$\langle h,r,t\rangle$，我们的目标是为每个实体学习一个更好的低维向量表示（$h$和$t$）和关系（$r$）在最小化拟合由机器学习（NELL）或众包（crowdsouring）给出的相应置信度的损失的过程中（Freebase），这样我们就可以在进行推理时使用$||{\bf h} + {\bf r} - {\bf t}||$来评估信念的可验证性。我们使用这些不精确的知识库的子集来训练我们的模型，并分别测试链接预测和三重分类对真实信念的性能。大量的实验结果表明，与基线和国家的最先进的方法相比，IIKE取得了显着的改善。
英文摘要：
This paper considers the problem of knowledge inference on large-scale imperfect repositories with incomplete coverage by means of embedding entities and relations at the first attempt. We propose IIKE (Imperfect and Incomplete Knowledge Embedding), a probabilistic model which measures the probability of each belief, i.e. $\langle h,r,t\rangle$, in large-scale knowledge bases such as NELL and Freebase, and our objective is to learn a better low-dimensional vector representation for each entity ($h$ and $t$) and relation ($r$) in the process of minimizing the loss of fitting the corresponding confidence given by machine learning (NELL) or crowdsouring (Freebase), so that we can use $||{\bf h} + {\bf r} - {\bf t}||$ to assess the plausibility of a belief when conducting inference. We use subsets of those inexact knowledge bases to train our model and test the performances of link prediction and triplet classification on ground truth beliefs, respectively. The results of extensive experiments show that IIKE achieves significant improvement compared with the baseline and state-of-the-art approaches.
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。
