Show simple item record

dc.contributor.authorLi, Sirui
dc.contributor.authorWong, Kok Wai
dc.contributor.authorFung, Chun Che
dc.contributor.authorZhu, Dengya
dc.identifier.citationLi, S. and Wong, K.W. and Fung, C.C. and Zhu, D. 2021. Improving Question Answering over Knowledge Graphs using Graph Summarization. In: International Conference on Neural Information Processing, 8th Dec 2021, Sanur, Bali, Indonesia.

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.

dc.titleImproving Question Answering over Knowledge Graphs using Graph Summarization
dc.typeConference Paper
dcterms.source.conferenceInternational Conference on Neural Information Processing
dcterms.source.conference-start-date8 Dec 2021
dcterms.source.conferencelocationSanur, Bali, Indonesia
curtin.departmentSchool of Management and Marketing
curtin.accessStatusFulltext not available
curtin.facultyFaculty of Business and Law
curtin.contributor.orcidZhu, Dengya [0000-0003-0818-437X]
dcterms.source.conference-end-date12 Dec 2021
curtin.contributor.scopusauthoridZhu, Dengya [22037238600]

Files in this item


This item appears in the following Collection(s)

Show simple item record