arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.11359cs.CL
收藏

知识图谱补全中长尾关系和非公共实体的处理

Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion

The Chinese University of Hong Kong(香港中文大学);Alibaba DAMO Academy(阿里巴巴达摩院);Tencent AI Lab(腾讯人工智能实验室)

Zihao Wang, Kwun Ping Lai, Piji Li, Lidong Bing, Wai Lam

摘要:

对于大规模的知识图谱,近年来的研究主要集中在大比例的非频繁关系上,而这些关系在以往的研究中被忽略了。例如,研究了关系的少样本学习范例。在这项工作中,我们进一步主张,处理不常见的实体是不可避免的,当处理罕见的关系。因此,我们提出了一个元学习框架,旨在通过使用文本描述来处理与少样本学习和不常见实体的不频繁关系。我们设计了一个新的模型,以更好地从文本描述中提取关键信息。此外,我们还在我们的框架中开发了一种新的生成模型,通过在训练阶段生成额外的三元组来提高性能。在两个真实世界的KG数据集上进行了实验,结果表明,我们的框架在处理不频繁关系及其伴随的不常见实体时优于以前的方法。

英文摘要:

For large-scale knowledge graphs (KGs), recent research has been focusing on the large proportion of infrequent relations which have been ignored by previous studies. For example few-shot learning paradigm for relations has been investigated. In this work, we further advocate that handling uncommon entities is inevitable when dealing with infrequent relations. Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions. We design a novel model to better extract key information from textual descriptions. Besides, we also develop a novel generative model in our framework to enhance the performance by generating extra triplets during the training stage. Experiments are conducted on two datasets from real-world KGs, and the results show that our framework outperforms previous methods when dealing with infrequent relations and their accompanying uncommon entities.

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。

↑