Advances in machine reading comprehension (MRC) rely heavily on the
collection of large scale human-annotated examples in the form of (question,
paragraph, answer) triples. In contrast, humans are typically able to
generalize with only a few examples, relying on deeper underlying world
knowledge, linguistic sophistication, and/or simply superior deductive powers.
In this paper, we focus on "teaching" machines reading comprehension, using a
small number of semi-structured explanations that explicitly inform machines
why answer spans are correct. We extract structured variables and rules from
explanations and compose neural module teachers that annotate instances for
training downstream MRC models. We use learnable neural modules and soft logic
to handle linguistic variation and overcome sparse coverage; the modules are
jointly optimized with the MRC model to improve final performance. On the SQuAD
dataset, our proposed method achieves 70.14% F1 score with supervision from 26
explanations, comparable to plain supervised learning using 1,100 labeled
instances, yielding a 12x speed up.

本文提出了一种使用少量半结构化解释 “教” 机器阅读理解的方法，同时提取结构化变量和规则，并组成神经模块作为下游 MRC 模型的训练实例的注释，使用可学习的神经模块和软逻辑来处理语言变化并克服模型覆盖率不足。在 SQuAD 数据集上，使用 26 个解释进行监督训练，该方法实现了 70.14% 的 F1 得分，与使用 1100 个标记实例的普通监督学习相比，速度提高了 12 倍。