Explanation Regeneration via Multi-Hop ILP Inference over Knowledge Base

Aayushee Gupta, Gopalakrishnan Srinivasaraghavan


Abstract
Textgraphs 2020 Workshop organized a shared task on ‘Explanation Regeneration’ that required reconstructing gold explanations for elementary science questions. This work describes our submission to the task which is based on multiple components: a BERT baseline ranking, an Integer Linear Program (ILP) based re-scoring and a regression model for re-ranking the explanation facts. Our system achieved a Mean Average Precision score of 0.3659.
Anthology ID:
2020.textgraphs-1.13
Volume:
Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
109–114
Language:
URL:
https://aclanthology.org/2020.textgraphs-1.13
DOI:
10.18653/v1/2020.textgraphs-1.13
Bibkey:
Cite (ACL):
Aayushee Gupta and Gopalakrishnan Srinivasaraghavan. 2020. Explanation Regeneration via Multi-Hop ILP Inference over Knowledge Base. In Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs), pages 109–114, Barcelona, Spain (Online). Association for Computational Linguistics.
Cite (Informal):
Explanation Regeneration via Multi-Hop ILP Inference over Knowledge Base (Gupta & Srinivasaraghavan, TextGraphs 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.textgraphs-1.13.pdf
Optional supplementary material:
 2020.textgraphs-1.13.OptionalSupplementaryMaterial.pdf