arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1506.01094cs.CLcs.AIcs.DBstat.ML
收藏

向量空间中知识图谱的遍历

Traversing Knowledge Graphs in Vector Space

Stanford University(斯坦福大学)

Kelvin Guu, John Miller, Percy Liang

摘要:

知识图谱上的路径查询可用于回答组合问题,例如“里斯本的人们说什么语言?".然而,知识图谱通常具有丢失的事实(边),这破坏了路径查询。最近的知识库补全模型通过在向量空间中嵌入知识图谱来估算缺失的事实。我们表明,这些模型可以递归地应用于回答路径查询,但他们遭受级联错误。这激发了一个新的“组合”训练目标,它大大提高了所有模型回答路径查询的能力,在某些情况下,准确率提高了一倍以上。在一个标准的知识库完成任务中,我们还证明了组合训练作为一种新的结构正则化形式,可靠地提高了所有基础模型的性能(将错误减少高达43%),并实现了新的最先进的结果。

英文摘要:

Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge graphs in vector spaces. We show that these models can be recursively applied to answer path queries, but that they suffer from cascading errors. This motivates a new "compositional" training objective, which dramatically improves all models' ability to answer path queries, in some cases more than doubling accuracy. On a standard knowledge base completion task, we also demonstrate that compositional training acts as a novel form of structural regularization, reliably improving performance across all base models (reducing errors by up to 43%) and achieving new state-of-the-art results.

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。

↑