REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement

TL;DR

This paper introduces REM-Net, a recursive erasure memory network that refines evidence for commonsense question answering by generating and iteratively removing low-quality evidence, improving answer accuracy and explainability.

Contribution

The paper presents a novel REM-Net model that generates customized evidence and recursively refines it by erasing low-quality information, enhancing evidence quality for commonsense QA.

Findings

REM-Net outperforms baseline models on WIQA and CosmosQA datasets.

Refined evidence improves answer accuracy and explainability.

Recursive erasure effectively filters out low-quality evidence.

Abstract

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. While recent works retrieve supporting facts/evidence from commonsense knowledge bases to supply additional information to each question, there is still ample opportunity to advance it on the quality of the evidence. It is crucial since the quality of the evidence is the key to answering commonsense questions, and even determines the upper bound on the QA systems performance. In this paper, we propose a recursive erasure memory network (REM-Net) to cope with the quality improvement of evidence. To address this, REM-Net is equipped with a module to refine the evidence by recursively erasing the low-quality evidence that does not explain the question answering. Besides, instead of retrieving evidence from existing knowledge bases, REM-Net leverages a pre-trained generative model to generate candidate evidence customized for the question. We conduct experiments on two commonsense question answering datasets, WIQA and CosmosQA. The results demonstrate the performance of REM-Net and show that the refined evidence is explainable.