Compositional Attention Networks for Interpretability in Natural Language Question Answering

Abstract-- MAC Net [3] is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. This makes it an ideal candidate for solving tasks that involve logical reasoning. Our experiments with 20 bAbI tasks, demonstrate the value of MAC net as a data-efficient and interpretable architecture for Natural Language Question Answering. The transparent nature of MAC net provides a highly granular view of the reasoning steps taken by the network in answering a query. There is a growing interest in the Machine Learning community to build explainable Artificial Intelligence.