Abstract
The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text, there have been no attempts to generate explanations of classifiers operating on pairs of sentences. In this paper, we show that it is possible to generate token-level explanations for NLI without the need for training data explicitly annotated for this purpose. We use a simple LSTM architecture and evaluate both LIME and Anchor explanations for this task. We compare these to a Multiple Instance Learning (MIL) method that uses thresholded attention make token-level predictions. The approach we present in this paper is a novel extension of zero-shot single-sentence tagging to sentence pairs for NLI. We conduct our experiments on the well-studied SNLI dataset that was recently augmented with manually annotation of the tokens that explain the entailment relation. We find that our white-box MIL-based method, while orders of magnitude faster, does not reach the same accuracy as the black-box methods.
Abstract (translated)
自然语言推理(nli)的任务被广泛地建模为监督语句对分类。虽然最近有很多关于在单个文本上生成分类器预测的解释的工作,但是没有尝试生成对句子操作的分类器的解释。在本文中,我们证明了可以生成NLI的令牌级解释,而不需要为此目的显式注释培训数据。我们使用一个简单的LSTM体系结构,并对这个任务的石灰和锚解释进行评估。我们将其与使用阈值注意进行令牌级预测的多实例学习(mil)方法进行比较。本文提出的方法是一种将NLI的零炮单句标记扩展到句子对的新方法。我们对研究得很好的snli数据集进行了实验,该数据集最近被手工添加了解释继承关系的标记注释。我们发现,我们的基于白盒密耳的方法,虽然数量级更快,但并没有达到与黑盒方法相同的精度。
URL
https://arxiv.org/abs/1904.10717