Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning

Yu Jin Kim, Beong-woo Kwak, Youngwook Kim, Reinald Kim Amplayo, Seung-won Hwang, Jinyoung Yeo


Abstract
Commonsense reasoning systems should be able to generalize to diverse reasoning cases. However, most state-of-the-art approaches depend on expensive data annotations and overfit to a specific benchmark without learning how to perform general semantic reasoning. To overcome these drawbacks, zero-shot QA systems have shown promise as a robust learning scheme by transforming a commonsense knowledge graph (KG) into synthetic QA-form samples for model training. Considering the increasing type of different commonsense KGs, this paper aims to extend the zero-shot transfer learning scenario into multiple-source settings, where different KGs can be utilized synergetically. Towards this goal, we propose to mitigate the loss of knowledge from the interference among the different knowledge sources, by developing a modular variant of the knowledge aggregation as a new zero-shot commonsense reasoning framework. Results on five commonsense reasoning benchmarks demonstrate the efficacy of our framework, improving the performance with multiple KGs.
Anthology ID:
2022.naacl-main.163
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2244–2257
Language:
URL:
https://aclanthology.org/2022.naacl-main.163
DOI:
10.18653/v1/2022.naacl-main.163
Bibkey:
Cite (ACL):
Yu Jin Kim, Beong-woo Kwak, Youngwook Kim, Reinald Kim Amplayo, Seung-won Hwang, and Jinyoung Yeo. 2022. Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2244–2257, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning (Kim et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.163.pdf
Video:
 https://aclanthology.org/2022.naacl-main.163.mp4
Data
ATOMICCommonsenseQAConceptNetPIQASIQA