Timezone: »

Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
Wangchunshu Zhou · Jinyi Hu · Hanlin Zhang · Xiaodan Liang · Maosong Sun · Chenyan Xiong · Jian Tang

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #721

Recently generating natural language explanations has shown very promising results in not only offering interpretable explanations but also providing additional information and supervision for prediction. However, existing approaches usually require a large set of human annotated explanations for training while collecting a large set of explanations is not only time consuming but also expensive. In this paper, we develop a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training. Our framework treats natural language explanations as latent variables that model the underlying reasoning process of a neural model. We develop a variational EM framework for optimization where an explanation generation module and an explanation-augmented prediction module are alternatively optimized and mutually enhance each other. Moreover, we further propose an explanation-based self-training method under this framework for semi-supervised learning. It alternates between assigning pseudo-labels to unlabeled data and generating new explanations to iteratively improve each other. Experiments on two natural language understanding tasks demonstrate that our framework can not only make effective predictions in both supervised and semi-supervised settings, but is also able to generate good natural language explanations.

Author Information

Wangchunshu Zhou (Beihang University)
Jinyi Hu (Tsinghua University)
Hanlin Zhang (South China University of Technology)
Xiaodan Liang (Sun Yat-sen University)
Maosong Sun (Tsinghua University)
Chenyan Xiong (Microsoft Research AI)
Jian Tang (Mila)

More from the Same Authors