论文标题
文本分类的无互连锁多效合理化
Interlock-Free Multi-Aspect Rationalization for Text Classification
论文作者
论文摘要
说明对于文本分类任务很重要。一种普遍的解释类型是理由，它们是输入文本的文本段，足以产生预测并且对人类有意义。关于合理化的大量研究是基于选择性合理化框架的，最近由于互锁动态而被证明是有问题的。在本文中，我们表明我们解决了多方面环境中的互锁问题，我们旨在为多个输出生成多个理由。更具体地说，我们提出了一种多阶段训练方法，该方法结合了额外的自我监督对比损失，有助于产生更多语义上不同的理由。啤酒评论数据集的经验结果表明，我们的方法可显着提高合理化的绩效。
Explanation is important for text classification tasks. One prevalent type of explanation is rationales, which are text snippets of input text that suffice to yield the prediction and are meaningful to humans. A lot of research on rationalization has been based on the selective rationalization framework, which has recently been shown to be problematic due to the interlocking dynamics. In this paper, we show that we address the interlocking problem in the multi-aspect setting, where we aim to generate multiple rationales for multiple outputs. More specifically, we propose a multi-stage training method incorporating an additional self-supervised contrastive loss that helps to generate more semantically diverse rationales. Empirical results on the beer review dataset show that our method improves significantly the rationalization performance.
