# Compositional Attention Networks for Interpretability in Natural Language Question Answering

arXiv: https://arxiv.org/abs/1810.12698 · HTML: https://mlsanity.com/paper/1810.12698/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2018.

## Built on by (most cited first, 1 of 1)

- [Compositional Attention: Disentangling Search and Retrieval](https://mlsanity.com/paper/2110.09419/) (2021)

## Abstract (arXiv)

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.