Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths

Haozhe Ji, Pei Ke, Shaohan Huang, Furu Wei, Minlie Huang


Abstract
Commonsense explanation generation aims to empower the machine’s sense-making capability by generating plausible explanations to statements against commonsense. While this task is easy to human, the machine still struggles to generate reasonable and informative explanations. In this work, we propose a method that first extracts the underlying concepts which are served as bridges in the reasoning chain and then integrates these concepts to generate the final explanation. To facilitate the reasoning process, we utilize external commonsense knowledge to build the connection between a statement and the bridge concepts by extracting and pruning multi-hop paths to build a subgraph. We design a bridge concept extraction model that first scores the triples, routes the paths in the subgraph, and further selects bridge concepts with weak supervision at both the triple level and the concept level. We conduct experiments on the commonsense explanation generation task and our model outperforms the state-of-the-art baselines in both automatic and human evaluation.
Anthology ID:
2020.aacl-main.28
Volume:
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
Month:
December
Year:
2020
Address:
Suzhou, China
Venue:
AACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
248–257
Language:
URL:
https://aclanthology.org/2020.aacl-main.28
DOI:
Bibkey:
Cite (ACL):
Haozhe Ji, Pei Ke, Shaohan Huang, Furu Wei, and Minlie Huang. 2020. Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 248–257, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths (Ji et al., AACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.aacl-main.28.pdf
Data
ConceptNet