Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method
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 focus 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 considier the incorrect predictions. Through a statistical analysis, we observe that models with stronger abilities do not predict less incorrect predictions compared to other models. In this work, we propose $\textbf{Answering-Classifying-Correcting}$ (ACC) framework, which employs a post-processing strategy to handle with incorrect predictions. Specifically, the ACC framework first introduces a $\textbf{classifier}$ to classify the predictions into three types and exclude "wrong predictions", then introduces a $\textbf{corrector}$ to modify "partially correct predictions". Experiments on four datasets show that ACC framework significantly improves the EM F1 scores of several MSQA models, and further analysis demostrate that ACC framework efficiently reduces the number of incorrect predictions, improving the quality of predictions. Our code and data are available at https://anonymous.4open.science/r/ACC-F6FB.
Paper Type: Long
Research Area: Question Answering
Research Area Keywords: reading comprehension
Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models
Languages Studied: English
Submission Number: 2086
Loading