KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

Bill Yuchen Lin, Xinyue Chen, Jamin Chen, Xiang Ren

[How to correct problems with metadata yourself]

Abstract
Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life. In this paper, we propose a textual inference framework for answering commonsense questions, which effectively utilizes external, structured commonsense knowledge graphs to perform explainable inferences. The framework first grounds a question-answer pair from the semantic space to the knowledge-based symbolic space as a schema graph, a related sub-graph of external knowledge graphs. It represents schema graphs with a novel knowledge-aware graph network module named KagNet, and finally scores answers with graph representations. Our model is based on graph convolutional networks and LSTMs, with a hierarchical path-based attention mechanism. The intermediate attention scores make it transparent and interpretable, which thus produce trustworthy inferences. Using ConceptNet as the only external resource for Bert-based models, we achieved state-of-the-art performance on the CommonsenseQA, a large-scale dataset for commonsense reasoning.
Anthology ID:
D19-1282
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2829–2839
Language:
URL:
https://aclanthology.org/D19-1282
DOI:
10.18653/v1/D19-1282
Bibkey:
Cite (ACL):
Bill Yuchen Lin, Xinyue Chen, Jamin Chen, and Xiang Ren. 2019. KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2829–2839, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning (Lin et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/D19-1282.pdf
Code
 INK-USC/KagNet +  additional community code
Data
CommonsenseQA, ConceptNet, SWAG, WSC
PDF Search Code