arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1412.6575cs.CL
收藏

知识库中用于学习和推理的实体和关系的嵌入

Embedding Entities and Relations for Learning and Inference in Knowledge Bases

Cornell University(康奈尔大学);Microsoft Research(微软研究院)

Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, Li Deng

摘要:

我们考虑使用神经嵌入方法学习知识库中实体和关系的表示。我们表明,大多数现有的模型,包括NTN(Socher等人,2013)和TransE(Bordes等人,2013 b),可以在统一的学习框架下推广,其中实体是从神经网络学习的低维向量,并且关系是双线性和/或线性映射函数。在这个框架下,我们比较了各种嵌入模型的链接预测任务。我们表明,一个简单的双线性公式实现了新的国家的最先进的结果的任务(实现了前10名的准确性为73.2%与54.7%的TransE的Freebase)。此外,我们引入了一种新的方法,利用学习的关系嵌入挖掘逻辑规则,如“BornInCity(a,b)和CityInCountry(b,c)=> Nationality(a,c)"。我们发现,嵌入学习的双线性目标是特别好的捕捉关系语义和组合关系的特点是矩阵乘法。更有趣的是,我们证明了我们的基于嵌入的规则提取方法成功地优于一个国家的最先进的基于信任的规则挖掘方法在挖掘霍恩规则,涉及组合推理。

英文摘要:

We consider learning representations of entities and relations in KBs using the neural-embedding approach. We show that most existing models, including NTN (Socher et al., 2013) and TransE (Bordes et al., 2013b), can be generalized under a unified learning framework, where entities are low-dimensional vectors learned from a neural network and relations are bilinear and/or linear mapping functions. Under this framework, we compare a variety of embedding models on the link prediction task. We show that a simple bilinear formulation achieves new state-of-the-art results for the task (achieving a top-10 accuracy of 73.2% vs. 54.7% by TransE on Freebase). Furthermore, we introduce a novel approach that utilizes the learned relation embeddings to mine logical rules such as "BornInCity(a,b) and CityInCountry(b,c) => Nationality(a,c)". We find that embeddings learned from the bilinear objective are particularly good at capturing relational semantics and that the composition of relations is characterized by matrix multiplication. More interestingly, we demonstrate that our embedding-based rule extraction approach successfully outperforms a state-of-the-art confidence-based rule mining approach in mining Horn rules that involve compositional reasoning.

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。

↑