REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement
This work aims to improve the quality of evidence for commonsense question answering systems, which is crucial for enhancing their performance.
This paper addresses the problem of low-quality evidence in commonsense question answering by proposing REM-Net, a recursive erasure memory network. REM-Net refines evidence by recursively erasing low-quality information and generates customized candidate evidence using a pre-trained generative model, demonstrating improved performance on WIQA and CosmosQA datasets.
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.