用后处理方法修正多段答案预测错误，提升准确率。
Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method
- 引入分类-修正框架，识别并修正错误答案
- 在多个数据集上显著提升精确匹配率（EM）
- 有效减少错误预测数量，适合需要高精度的应用
多段问答（MSQA）要求模型从上下文中提取一个或多个答案片段来回答问题。以往工作主要关注设计特定方法或应用启发式策略以提高正确预测率，但这些模型在黄金答案上训练，未考虑错误预测。通过统计分析发现，能力强的模型也并不比其他模型少产生错误预测。为此，本文提出答案分类修正（ACC）框架，采用后处理策略处理错误预测。具体地，先用分类器将预测分为三类并剔除“错误预测”，再用修正器修改“部分正确预测”。在多个MSQA数据集上的实验表明，该框架显著提升了精确匹配（EM）分数，进一步分析显示其有效减少了错误预测数量，提升了预测质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。