arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.01341cs.AIcs.CLstat.ML
收藏

嵌入多模态关系数据实现知识库完备

Embedding Multimodal Relational Data for Knowledge Base Completion

University of California(加利福尼亚大学)

Pouya Pezeshkpour, Liyan Chen, Sameer Singh

摘要:

在嵌入空间中表示实体和关系是关系数据上的机器学习的一种经过充分研究的方法。然而,现有的方法主要集中在有限实体集之间的简单链接结构上,忽略了知识库中经常使用的各种数据类型,例如文本、图像和数值。在本文中,我们提出了多模态知识库嵌入(MKBE),使用不同的神经编码器的各种观察到的数据,并将它们与现有的关系模型学习嵌入的实体和多模态数据。此外,使用这些学习的嵌入和不同的神经解码器,我们引入了一种新的多模态插补模型,从知识库中的信息中生成缺失的多模态值,如文本和图像。我们丰富现有的关系数据集,创建两个新的基准,包含额外的信息,如文本描述和原始实体的图像。我们证明,我们的模型有效地利用这些额外的信息,以提供更准确的链接预测,实现国家的最先进的结果与现有的方法有相当大的差距5-7%。此外,我们通过用户研究来评估我们生成的多模态值的质量。我们在https://github.com/pouyapez/mkbe上发布了数据集和模型的开源实现

英文摘要:

Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data. Existing approaches, however, primarily focus on simple link structure between a finite set of entities, ignoring the variety of data types that are often used in knowledge bases, such as text, images, and numerical values. In this paper, we propose multimodal knowledge base embeddings (MKBE) that use different neural encoders for this variety of observed data, and combine them with existing relational models to learn embeddings of the entities and multimodal data. Further, using these learned embedings and different neural decoders, we introduce a novel multimodal imputation model to generate missing multimodal values, like text and images, from information in the knowledge base. We enrich existing relational datasets to create two novel benchmarks that contain additional information such as textual descriptions and images of the original entities. We demonstrate that our models utilize this additional information effectively to provide more accurate link prediction, achieving state-of-the-art results with a considerable gap of 5-7% over existing methods. Further, we evaluate the quality of our generated multimodal values via a user study. We have release the datasets and the open-source implementation of our models at https://github.com/pouyapez/mkbe

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。

↑