Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference

Autor: Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, André Freitas
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: Transactions of the Association for Computational Linguistics, Vol 10, Pp 1103-1119 (2022)
Druh dokumentu: article
ISSN: 2307-387X
DOI: 10.1162/tacl_a_00508/113021/Diff-Explainer-Differentiable-Convex-Optimization
Popis: AbstractThis 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.
Databáze: Directory of Open Access Journals