2020
COLING
COLING 2020
Explanation Regeneration via Multi-Hop ILP Inference over Knowledge Base
Abstract
AbstractTextgraphs 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.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Knowledge & Reasoning and Natural Language Processing
Topics
Artificial Intelligence > Core AI > Interpretability
Natural Language Processing > Applications > Question Answering
Knowledge & Reasoning > Representation > Knowledge Graphs
Knowledge & Reasoning > Reasoning > Automated Reasoning
Natural Language Processing > Applications > Natural Language Inference