Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor. However, rationalization suffers from two key challenges, i.e., spurious correlation and degeneration, where the predictor overfits the spurious or meaningless pieces solely selected by the not-yet well-trained generator and in turn deteriorates the generator. Although many studies have been proposed to address the two challenges, they are usually designed separately and do not take both of them into account. In this paper, we propose a simple yet effective method named MGR to simultaneously solve the two problems. The key idea of MGR is to employ multiple generators such that the occurrence stability of real pieces is improved and more meaningful pieces are delivered to the predictor. Empirically, we show that MGR improves the F1 score by up to 20.9% as compared to state-of-the-art methods. Codes are available at https://github.com/jugechengzi/Rationalization-MGR .

翻译：可解释性是指利用生成器与预测器构建自解释自然语言处理模型，其中生成器从输入文本中筛选出符合人类可读性的子集，以供后续预测器使用。然而，可解释性面临两大关键挑战：虚假相关性与退化问题。前者指预测器过度依赖尚未充分训练的生成器所选取的虚假或无意义片段，后者则导致生成器性能恶化。尽管已有诸多研究分别针对这两类挑战提出解决方案，但鲜有方法能同时处理两者。本文提出一种名为MGR的简洁高效方法，可同步解决上述问题。其核心思想在于采用多个生成器，通过提升真实片段出现稳定性，向预测器提供更富意义的文本片段。实验表明，相较于现有最优方法，MGR最高可将F1分数提升20.9%。代码已开源至https://github.com/jugechengzi/Rationalization-MGR。