Natural language inference (NLI) is the task of detecting the existence of entailment or contradiction in a given sentence pair. Although NLI techniques could help numerous information retrieval tasks, most solutions for NLI are neural approaches whose lack of interpretability prohibits both straightforward integration and diagnosis for further improvement. We target the task of generating token-level explanations for NLI from a neural model. Many existing approaches for token-level explanation are either computationally costly or require additional annotations for training. In this article, we first introduce a novel method for training an explanation generator that does not require additional human labels. Instead, the explanation generator is trained with the objective of predicting how the model’s classification output will change when parts of the inputs are modified. Second, we propose to build an explanation generator in a multi-task learning setting along with the original NLI task so the explanation generator can utilize the model’s internal behavior. The experiment results suggest that the proposed explanation generator outperforms numerous strong baselines. In addition, our method does not require excessive additional computation at prediction time, which renders it an order of magnitude faster than the best-performing baseline.

中文翻译：

---

解释神经自然语言推理中的文本匹配

自然语言推理 (NLI) 是检测给定句子对中是否存在蕴涵或矛盾的任务。尽管 NLI 技术可以帮助许多信息检索任务，但 NLI 的大多数解决方案都是神经方法，其缺乏可解释性阻碍了直接集成和进一步改进的诊断。我们的目标是从神经模型中为 NLI 生成令牌级别的解释。许多现有的令牌级解释方法要么计算成本高，要么需要额外的注释进行训练。在本文中，我们首先介绍了一种无需额外人工标签即可训练解释生成器的新方法。反而，解释生成器的训练目标是预测当部分输入被修改时模型的分类输出将如何变化。其次，我们建议在多任务学习环境中与原始 NLI 任务一起构建解释生成器，以便解释生成器可以利用模型的内部行为。实验结果表明，所提出的解释生成器优于许多强基线。此外，我们的方法在预测时不需要过多的额外计算，这使其比性能最佳的基线快一个数量级。实验结果表明，所提出的解释生成器优于许多强基线。此外，我们的方法在预测时不需要过多的额外计算，这使其比性能最佳的基线快一个数量级。实验结果表明，所提出的解释生成器优于许多强基线。此外，我们的方法在预测时不需要过多的额外计算，这使其比性能最佳的基线快一个数量级。