Compositional Attention Networks for Interpretability in Natural Language Question Answering

TL;DR

This paper introduces a modified MAC Net architecture tailored for natural language question answering, emphasizing interpretability and iterative reasoning, demonstrated through experiments on 20 bAbI tasks.

Contribution

It adapts the MAC Net architecture for NLP tasks, enhancing interpretability and reasoning capabilities in question answering.

Findings

Effective on 20 bAbI tasks

Data-efficient and interpretable reasoning

Provides granular view of reasoning steps

Abstract

MAC Net 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. MAC net's unique architecture - the separation between memory and control, facilitates data-driven iterative 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.