While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing neural predictions by highlighting salient concepts in the text as justifications or rationales, they rely on thousands of labeled training examples for both task labels as well as an-notated rationales for every instance. Such extensive large-scale annotations are infeasible to obtain for many tasks. To this end, we develop a multi-task teacher-student framework based on self-training language models with limited task-specific labels and rationales, and judicious sample selection to learn from informative pseudo-labeled examples1. We study several characteristics of what constitutes a good rationale and demonstrate that the neural model performance can be significantly improved by making it aware of its rationalized predictions, particularly in low-resource settings. Extensive experiments in several bench-mark datasets demonstrate the effectiveness of our approach.
翻译:虽然经过培训的语文模式在几项自然语言理解任务中取得了最先进的表现,但在决策过程方面却相当不透明。虽然最近的一些工作侧重于通过强调案文中突出的概念作为理由或理由,使神经预测合理化,但是它们依赖数千个标有标签的培训范例来标注两种任务标签以及每个任务的说明理由。这种广泛的大规模说明对于许多任务来说是行不通的。为此,我们制定了一个多任务教师-学生框架,其基础是自我培训语言模式,其特定任务标签和理由有限,以及明智的抽样选择,以便从信息化的假标签实例中学习。1 我们研究构成良好理由的若干特征,并表明通过了解其合理预测,特别是在低资源环境中的预测,可以大大改进神经模型的性能。在几个基准数据集中进行的广泛实验表明我们的方法的有效性。