Explainable neural computation via stack neural module networks

Abstract

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 subtask decomposition without relying on strong supervision. Our model allows linking different reasoning tasks through 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.

Development and Evaluation of a Natural Language Processing System for Curating a Trans-Thoracic Echocardiogram (TTE) Database

“…By concentrating on training component modules and learning how to combine them, this method minimises the need to relearn for every type of issue. The JAPE rules as part of the JAVA interfacing NLP system in this study have similarities in principle to the methodology for composing NMNs modules [38], and may provide the basis for integrating neural based approaches to TTE extraction systems in an interpretable manner. For studies have generally focusing on image based problems, the attention module generally prefers the use of attention extracted from Convolution Neural Networks [39,40].…”