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 2203.13570cs.LG
收藏

利用图摘要改进基于知识图谱的问答

Improving Question Answering over Knowledge Graphs Using Graph Summarization

Murdoch University(莫道克大学);Curtin University(科廷大学)

Sirui Li, Kok Kai Wong, Dengya Zhu, Chun Che Fung

摘要:

基于知识图谱(KG)的问答(QA)系统(KGQA)使用包含在KG中的三元组自动回答自然语言问题。关键思想是将KG的问题和实体表示为低维嵌入。先前的KGQA已经尝试使用知识图谱嵌入(KGE)和深度学习(DL)方法来表示实体。然而,KGE太浅,无法捕获表达功能,DL方法独立地处理每个三元组。最近,图卷积网络(GCN)已被证明是优秀的提供实体嵌入。然而,使用GCN到KGQA是低效的,因为GCN在聚合邻域时平等地对待所有关系。此外,在使用以前的KGQA时可能会出现问题:在大多数情况下,问题通常有不确定的答案数量。为了解决上述问题,我们提出了一种使用递归卷积神经网络(RCNN)和GCN的图形摘要技术。GCN和RCNN的结合确保了嵌入与问题相关的关系一起传播,从而获得更好的答案。所提出的图摘要技术可以用来解决KGQA不能回答具有不确定数量的答案的问题。在本文中,我们展示了最常见的问题类型,这是单关系问题的建议的技术。实验表明,与GCN相比,使用RCNN和GCN的所提出的图摘要技术可以提供更好的结果。当问题的答案数量不确定时,所提出的图摘要技术显著提高了实际答案的召回率。

英文摘要:

Question Answering (QA) systems over Knowledge Graphs (KGs) (KGQA) automatically answer natural language questions using triples contained in a KG. The key idea is to represent questions and entities of a KG as low-dimensional embeddings. Previous KGQAs have attempted to represent entities using Knowledge Graph Embedding (KGE) and Deep Learning (DL) methods. However, KGEs are too shallow to capture the expressive features and DL methods process each triple independently. Recently, Graph Convolutional Network (GCN) has shown to be excellent in providing entity embeddings. However, using GCNs to KGQAs is inefficient because GCNs treat all relations equally when aggregating neighbourhoods. Also, a problem could occur when using previous KGQAs: in most cases, questions often have an uncertain number of answers. To address the above issues, we propose a graph summarization technique using Recurrent Convolutional Neural Network (RCNN) and GCN. The combination of GCN and RCNN ensures that the embeddings are propagated together with the relations relevant to the question, and thus better answers. The proposed graph summarization technique can be used to tackle the issue that KGQAs cannot answer questions with an uncertain number of answers. In this paper, we demonstrated the proposed technique on the most common type of questions, which is single-relation questions. Experiments have demonstrated that the proposed graph summarization technique using RCNN and GCN can provide better results when compared to the GCN. The proposed graph summarization technique significantly improves the recall of actual answers when the questions have an uncertain number of answers.

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。

↑