Bilinear Graph Neural Network-Based Reasoning for Multi-Hop Question Answering


KIPS Transactions on Software and Data Engineering, Vol. 9, No. 8, pp. 243-250, Aug. 2020
https://doi.org/10.3745/KTSDE.2020.9.8.243,   PDF Download:
Keywords: Open Domain Question Answering, Knowledge Graph, Complex Question, Graph Neural Network
Abstract

Knowledge graph-based question answering not only requires deep understanding of the given natural language questions, but it also needs effective reasoning to find the correct answers on a large knowledge graph. In this paper, we propose a deep neural network model for effective reasoning on a knowledge graph, which can find correct answers to complex questions requiring multi-hop inference. The proposed model makes use of highly expressive bilinear graph neural network (BGNN), which can utilize context information between a pair of neighboring nodes, as well as allows bidirectional feature propagation between each entity node and one of its neighboring nodes on a knowledge graph. Performing experiments with an open-domain knowledge base (Freebase) and two natural-language question answering benchmark datasets(WebQuestionsSP and MetaQA), we demonstrate the effectiveness and performance of the proposed model.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
S. Lee and I. Kim, "Bilinear Graph Neural Network-Based Reasoning for Multi-Hop Question Answering," KIPS Transactions on Software and Data Engineering, vol. 9, no. 8, pp. 243-250, 2020. DOI: https://doi.org/10.3745/KTSDE.2020.9.8.243.

[ACM Style]
Sangui Lee and Incheol Kim. 2020. Bilinear Graph Neural Network-Based Reasoning for Multi-Hop Question Answering. KIPS Transactions on Software and Data Engineering, 9, 8, (2020), 243-250. DOI: https://doi.org/10.3745/KTSDE.2020.9.8.243.