Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that reasons about complex questions by decomposing them to simpler subquestions that can take advantage of single-span extraction reading-comprehension models, and derives the final answer according to instructions in a predefined reasoning template. We focus on subtraction-based arithmetic questions and evaluate our approach on a subset of the DROP dataset. We show that our approach is competitive with the state-of-the-art while being interpretable and requires little supervision

翻译：从一段段落的多个部分获得信息以获得答案,这是对阅读综合模型的公开挑战。在本文中,我们提出一种方法,将复杂问题的理由分为简单的子问题,这些子问题可以利用单一的提取阅读综合模型,并按照预先定义的推理模板中的指示得出最后答案。我们侧重于减法计算问题,对DROP数据集的一个子集评估我们的方法。我们表明,我们的方法在与最新技术竞争的同时是可以解释的,不需要多少监督。