Prediction without justification has limited applicability. As a remedy, we
learn to extract pieces of input text as justifications -- rationales -- that
are tailored to be short and coherent, yet sufficient for making the same
prediction. Our approach combines two modular components, generator and
encoder, which are trained to operate well together. The generator specifies a
distribution over text fragments as candidate rationales and these are passed
through the encoder for prediction. Rationales are never given during training.
Instead, the model is regularized by desiderata for rationales. We evaluate the
approach on multi-aspect sentiment analysis against manually annotated test
cases. Our approach outperforms attention-based baseline by a significant
margin. We also successfully illustrate the method on the question retrieval
task.

通过提取文本来生成短而连贯的理由 —— 根据规则确保足以做出准确预测的 —— 以代替不带理由的预测，该方法结合了生成器（分配文本碎片的候选理由）和编码器（用于预测）。从未给予判据，而是让模型符合对规则的要求。本文还在多方面情感分析和问题检索任务中成功验证了此方法。