WT5?! Training Text-to-Text Models to Explain their Predictions
Sharan Narang Colin Raffel Katherine Lee Adam Roberts Noah Fiedel Karishma Malkan Google Research Equal Contribution. Correspondence to
Abstract
Neural networks have recently achieved human-level performance on various challenging natural language processing (NLP) tasks, but it is notoriously difficult to understand why a neural network produced a particular prediction. In this paper, we leverage the text-to-text framework proposed by Raffel et al. (2019) to train language models to output a natural text explanation alongside their prediction. Crucially, this requires no modifications to the loss function or training and decoding procedures – we simply train the model to output the explanation after generating the (natural text) prediction. We show that this approach not only obtains state-of-the-art results on “explainability” benchmarks, but also permits learning from a limited set of labeled explanations and transferring rationalization abilities across datasets. To facilitate reproducibility and future work, we release our code use to train the models.111https://github.com/google-research/google-research/tree/master/wt5
中文速览
神经网络在自然语言处理任务上表现出色，却像个"黑盒子"，让人搞不清楚它为什么做出某个判断。研究者们借助 T5 这个"文本输入、文本输出"的预训练模型，用一个极其简单的办法让模型在给出预测的同时自动生成自然语言解释——只需在输入前加"explain"、在输出后追加解释文字，完全不用改动损失函数或训练流程。实验结果表明，这种方法（被命名为 WT5）不仅在多个可解释性基准测试上达到了当时的最优水平，还能在只有少量标注解释的半监督场景下有效学习，并且把"会解释"的能力迁移到训练时从未见过的数据集上。这项工作的意义在于：它证明了让模型用大白话"说清楚自己的想法"是可行且高效的，为神经网络可解释性研究提供了一条不依赖特殊架构的新路径。
原文 arXiv:2004.14546;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2004.14546v1