# Compositional Attention Networks for Interpretability in Natural Language Question Answering

Source: [Compositional Attention Networks for Interpretability in Natural Language Question Answering](<https://www.sota2.com/research/paper/68fa65011e209131cea07ca4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:16:52.800Z

Authors: Muru Selvakumar, Suriyadeepan Ramamoorthy, Vaidheeswaran Archana, Malaikannan Sankarasubbu

Published: 2018-10-30T12:23:35.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1810.12698>)

[PDF](<https://arxiv.org/pdf/1810.12698.pdf>)