Unification-based Reconstruction of Multi-hop Explanations for Science Questions

Marco Valentino, Mokanarangan Thayaparan, André Freitas


Abstract
This paper presents a novel framework for reconstructing multi-hop explanations in science Question Answering (QA). While existing approaches for multi-hop reasoning build explanations considering each question in isolation, we propose a method to leverage explanatory patterns emerging in a corpus of scientific explanations. Specifically, the framework ranks a set of atomic facts by integrating lexical relevance with the notion of unification power, estimated analysing explanations for similar questions in the corpus. An extensive evaluation is performed on the Worldtree corpus, integrating k-NN clustering and Information Retrieval (IR) techniques. We present the following conclusions: (1) The proposed method achieves results competitive with Transformers, yet being orders of magnitude faster, a feature that makes it scalable to large explanatory corpora (2) The unification-based mechanism has a key role in reducing semantic drift, contributing to the reconstruction of many hops explanations (6 or more facts) and the ranking of complex inference facts (+12.0 Mean Average Precision) (3) Crucially, the constructed explanations can support downstream QA models, improving the accuracy of BERT by up to 10% overall.
Anthology ID:
2021.eacl-main.15
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
200–211
Language:
URL:
https://aclanthology.org/2021.eacl-main.15
DOI:
10.18653/v1/2021.eacl-main.15
Bibkey:
Cite (ACL):
Marco Valentino, Mokanarangan Thayaparan, and André Freitas. 2021. Unification-based Reconstruction of Multi-hop Explanations for Science Questions. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 200–211, Online. Association for Computational Linguistics.
Cite (Informal):
Unification-based Reconstruction of Multi-hop Explanations for Science Questions (Valentino et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.15.pdf
Code
 ai-systems/unification_reconstruction_explanations
Data
ARC (AI2 Reasoning Challenge)Worldtree