Explainable Neural Computation via Stack Neural Module Networks

07/23/2018
by   Ronghang Hu, et al.
0

In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be interpretable to assist users in both development and prediction. Existing models designed to produce interpretable traces of their decision-making process typically require these traces to be supervised at training time. In this paper, we present a novel neural modular approach that performs compositional reasoning by automatically inducing a desired sub-task decomposition without relying on strong supervision. Our model allows linking different reasoning tasks though shared modules that handle common routines across tasks. Experiments show that the model is more interpretable to human evaluators compared to other state-of-the-art models: users can better understand the model's underlying reasoning procedure and predict when it will succeed or fail based on observing its intermediate outputs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/25/2022

From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering

In order to achieve a general visual question answering (VQA) system, it...
research
04/14/2022

Measuring Compositional Consistency for Video Question Answering

Recent video question answering benchmarks indicate that state-of-the-ar...
research
10/20/2022

Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformers

This paper presents ReasonFormer, a unified reasoning framework for mirr...
research
03/14/2018

Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning

Visual question answering requires high-order reasoning about an image, ...
research
05/02/2020

Obtaining Faithful Interpretations from Compositional Neural Networks

Neural module networks (NMNs) are a popular approach for modeling compos...
research
10/03/2020

Towards Interpretable Reasoning over Paragraph Effects in Situation

We focus on the task of reasoning over paragraph effects in situation, w...
research
01/04/2023

Iterated Decomposition: Improving Science Q A by Supervising Reasoning Processes

Language models (LMs) can perform complex reasoning either end-to-end, w...

Please sign up or login with your details

Forgot password? Click here to reset