Not logged in.

Contribution Details

Type Working Paper
Scope Discipline-based scholarship
Title QAGCN: A Graph Convolutional Network-based Multi-Relation Question Answering System
Organization Unit
  • Ruijie Wang
  • Luca Rossetto
  • Michael Cochez
  • Abraham Bernstein
  • English
Institution Cornell University
Series Name
Number 2206.01818
ISSN 2331-8422
Number of Pages 19
Date 2022
Abstract Text Answering multi-relation questions over knowledge graphs is a challenging task as it requires multi-step reasoning over a huge number of possible paths. Reasoning-based methods with complex reasoning mechanisms, such as reinforcement learning-based sequential decision making, have been regarded as the default pathway for this task. However, these mechanisms are difficult to implement and train, which hampers their reproducibility and transferability to new domains. In this paper, we propose QAGCN - a simple but effective and novel model that leverages attentional graph convolutional networks that can perform multi-step reasoning during the encoding of knowledge graphs. As a consequence, complex reasoning mechanisms are avoided. In addition, to improve efficiency, we retrieve answers using highly-efficient embedding computations and, for better interpretability, we extract interpretable paths for returned answers. On widely adopted benchmark datasets, the proposed model has been demonstrated competitive against state-of-the-art methods that rely on complex reasoning mechanisms. We also conducted extensive experiments to scrutinize the efficiency and contribution of each component of our model.
Free access at DOI
Digital Object Identifier 10.48550/arXiv.2206.01818
Other Identification Number merlin-id:22574
PDF File Download from ZORA
Export BibTeX