Graph Reasoning and Context Fusion for Multi-Task, Multi-Hop Question Answering


KIPS Transactions on Software and Data Engineering, Vol. 10, No. 8, pp. 319-330, Aug. 2021
https://doi.org/10.3745/KTSDE.2021.10.8.319,   PDF Download:  
Keywords: Open Domain Question Answering, Multi-hop Reasoning, Multi-task Question, Hierarchical Graph, Graph Neural Network
Abstract

Recently, in the field of open domain natural language question answering, multi-task, multi-hop question answering has been studied extensively. In this paper, we propose a novel deep neural network model using hierarchical graphs to answer effectively such multi-task, multi-hop questions. The proposed model extracts different levels of contextual information from multiple paragraphs using hierarchical graphs and graph neural networks, and then utilize them to predict answer type, supporting sentences and answer spans simultaneously. Conducting experiments with the HotpotQA benchmark dataset, we show high performance and positive effects 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, "Graph Reasoning and Context Fusion for Multi-Task, Multi-Hop Question Answering," KIPS Transactions on Software and Data Engineering, vol. 10, no. 8, pp. 319-330, 2021. DOI: https://doi.org/10.3745/KTSDE.2021.10.8.319.

[ACM Style]
Sangui Lee and Incheol Kim. 2021. Graph Reasoning and Context Fusion for Multi-Task, Multi-Hop Question Answering. KIPS Transactions on Software and Data Engineering, 10, 8, (2021), 319-330. DOI: https://doi.org/10.3745/KTSDE.2021.10.8.319.