In this paper, we describe our mUlti-task learNIng for cOmmonsense reasoNing (UNION) system submitted for Task C of the SemEval2020 Task 4, which is to generate a reason explaining why a given false statement is non-sensical. However, we found in the early experiments that simple adaptations such as fine-tuning GPT2 often yield dull and non-informative generations (e.g. simple negations). In order to generate more meaningful explanations, we propose UNION, a unified end-to-end framework, to utilize several existing commonsense datasets so that it allows a model to learn more dynamics under the scope of commonsense reasoning. In order to perform model selection efficiently, accurately and promptly, we also propose a couple of auxiliary automatic evaluation metrics so that we can extensively compare the models from different perspectives. Our submitted system not only results in a good performance in the proposed metrics but also outperforms its competitors with the highest achieved score of 2.10 for human evaluation while remaining a BLEU score of 15.7. Our code is made publicly available at GitHub.

中文翻译：

---

SemEval-2020 上的 ANA 任务 4：常识推理的多任务学习 (UNION)

在本文中，我们描述了我们为 SemEval2020 任务 4 的任务 C 提交的常识推理 (UNION) 系统的多任务学习，这是为了产生解释为什么给定的错误陈述是无意义的原因。然而，我们在早期的实验中发现，诸如微调 GPT2 之类的简单适应通常会产生沉闷和无信息的生成（例如简单的否定）。为了产生更有意义的解释，我们提出了统一的端到端框架 UNION，以利用几个现有的常识数据集，以便它允许模型在常识推理的范围内学习更多动态。为了高效、准确、及时地进行模型选择，我们还提出了几个辅助的自动评估指标，以便我们可以从不同的角度对模型进行广泛的比较。我们提交的系统不仅在建议的指标中取得了良好的表现，而且在人类评估方面的最高得分为 2.10，同时保持了 15.7 的 BLEU 得分。我们的代码在 GitHub 上公开提供。