Graph attention network with edge weights for question answering over knowledge graph

Junzhe Li; Xia Hou

doi:10.1117/12.2637109

15 June 2022 Graph attention network with edge weights for question answering over knowledge graph

Junzhe Li, Xia Hou

Proceedings Volume 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022); 122850Q (2022) https://doi.org/10.1117/12.2637109
Event: International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 2022, Zhuhai, China

Abstract

Question Answering over the Knowledge Graphs (KGQA) has attracted extensive attention. The graph neural network can represent the dependent information of the KG, so it is well applied to the KGQA. But most of the KGQA approaches based on graph neural networks model question sentences and candidate answer entities separately. And the influences among questions, relations, and structure are not fully utilized when learning entity representations. To solve these problems, it is proposed that a question answering method based on graph attention network with edge weight to enhance the question relevance of entity representation. For the relationship in the extracted candidate answer subgraph, the Roberta is used to calculate the question’s semantic similarity to be the edge weight. A graph attention network is relied on to fuse the pre-trained entity embeddings and edge weight information for node updates to obtain candidate answer representations. The experimental results show that our proposed model has certain advantages compared with some other benchmark methods.

Citation Download Citation

Junzhe Li and Xia Hou "Graph attention network with edge weights for question answering over knowledge graph", Proc. SPIE 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 122850Q (15 June 2022); https://doi.org/10.1117/12.2637109

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available