We present an accurate and interpretable method for answer extraction in machine reading comprehension that is reminiscent of case-based reasoning (CBR) from classical AI. Our method (CBR-MRC) builds upon the hypothesis that contextualized answers to similar questions share semantic similarities with each other. Given a test question, CBR-MRC first retrieves a set of similar cases from a nonparametric memory and then predicts an answer by selecting the span in the test context that is most similar to the contextualized representations of answers in the retrieved cases. The semi-parametric nature of our approach allows it to attribute a prediction to the specific set of evidence cases, making it a desirable choice for building reliable and debuggable QA systems. We show that CBR-MRC provides high accuracy comparable with large reader models and outperforms baselines by 11.5 and 8.4 EM on NaturalQuestions and NewsQA, respectively. Further, we demonstrate the ability of CBR-MRC in identifying not just the correct answer tokens but also the span with the most relevant supporting evidence. Lastly, we observe that contexts for certain question types show higher lexical diversity than others and find that CBR-MRC is robust to these variations while performance using fully-parametric methods drops.

翻译：我们提出了一种精确且可解释的机器阅读理解答案提取方法，该方法借鉴了经典人工智能中的案例推理思想。我们的方法（CBR-MRC）基于以下假设：相似问题的上下文答案在语义上具有相似性。给定一个测试问题，CBR-MRC首先从非参数记忆库中检索一组相似案例，然后通过选择测试上下文中最相似于检索案例中答案上下文表示的跨度来预测答案。该方法的半参数特性允许其将预测归因于特定的证据案例集，使其成为构建可靠且可调试的问答系统的理想选择。我们证明，CBR-MRC提供的准确率与大型阅读模型相当，并在NaturalQuestions和NewsQA数据集上分别以11.5和8.4的精确匹配指标超越了基线方法。此外，我们展示了CBR-MRC不仅能识别正确的答案标记，还能识别包含最相关支持证据的跨度。最后，我们观察到某些问题类型的上下文比其它类型表现出更高的词汇多样性，并发现CBR-MRC对这些变化具有鲁棒性，而全参数方法的性能则会下降。