Skip Nav Destination
Close Modal
Update search
NARROW
Format
Journal
Date
Availability
1-1 of 1
Mokanarangan Thayaparan
Close
Follow your search
Access your saved searches in your account
Would you like to receive an alert when new items match your search?
Sort by
Journal Articles
Publisher: Journals Gateway
Transactions of the Association for Computational Linguistics (2022) 10: 1103–1119.
Published: 19 September 2022
FIGURES
| View All (4)
Abstract
View article
PDF
This paper presents Diff- Explainer, the first hybrid framework for explainable multi-hop inference that integrates explicit constraints with neural architectures through differentiable convex optimization. Specifically, Diff- Explainer allows for the fine-tuning of neural representations within a constrained optimization framework to answer and explain multi-hop questions in natural language. To demonstrate the efficacy of the hybrid framework, we combine existing ILP-based solvers for multi-hop Question Answering (QA) with Transformer-based representations. An extensive empirical evaluation on scientific and commonsense QA tasks demonstrates that the integration of explicit constraints in a end-to-end differentiable framework can significantly improve the performance of non- differentiable ILP solvers (8.91%–13.3%). Moreover, additional analysis reveals that Diff- Explainer is able to achieve strong performance when compared to standalone Transformers and previous multi-hop approaches while still providing structured explanations in support of its predictions.