Many natural language questions require qualitative, quantitative or logical
comparisons between two entities or events. This paper addresses the problem of
improving the accuracy and consistency of responses to comparison questions by
integrating logic rules and neural models. Our method leverages logical and
linguistic knowledge to augment labeled training data and then uses a
consistency-based regularizer to train the model. Improving the global
consistency of predictions, our approach achieves large improvements over
previous methods in a variety of question answering (QA) tasks including
multiple-choice qualitative reasoning, cause-effect reasoning, and extractive
machine reading comprehension. In particular, our method significantly improves
the performance of RoBERTa-based models by 1-5% across datasets. We advance the
state of the art by around 5-8% on WIQA and QuaRel and reduce consistency
violations by 58% on HotpotQA. We further demonstrate that our approach can
learn effectively from limited data.

本文通过整合逻辑规则和神经模型，使用基于一致性的正则化来提高问答任务中对比问题的响应的准确性和一致性，该方法在各种问题回答（QA）任务中获得大幅提高。特别是，在数据集中，我们的方法使 RoBERTa 模型的性能提高了 1-5％，，并在 WIQA 和 QuaRel 上将现有技术水平提高了约 5-8％，在 HotpotQA 上减少一致性违规 58％。同时，我们进一步证明了我们的方法可以从有限的数据中有效地学习。