Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method

TL;DR

This paper introduces the ACC framework, a post-processing method for multi-span question answering that classifies and corrects predictions to improve accuracy and reduce errors.

Contribution

It proposes a novel post-processing approach with a classifier and corrector to enhance multi-span QA performance beyond existing methods.

Findings

Significant improvement in Exact Match scores on multiple datasets

Effective reduction of incorrect predictions

Enhanced prediction quality through classification and correction

Abstract

Multi-Span Question Answering (MSQA) requires models to extract one or multiple answer spans from a given context to answer a question. Prior work mainly focuses on designing specific methods or applying heuristic strategies to encourage models to predict more correct predictions. However, these models are trained on gold answers and fail to consider the incorrect predictions. Through a statistical analysis, we observe that models with stronger abilities do not predict less incorrect predictions compared with other models. In this work, we propose Answering-Classifying-Correcting (ACC) framework, which employs a post-processing strategy to handle incorrect predictions. Specifically, the ACC framework first introduces a classifier to classify the predictions into three types and exclude "wrong predictions", then introduces a corrector to modify "partially correct predictions". Experiments on several MSQA datasets show that ACC framework significantly improves the Exact Match (EM) scores, and further analysis demostrates that ACC framework efficiently reduces the number of incorrect predictions, improving the quality of predictions.