Learning to Read through Machine Teaching

TL;DR

This paper explores how structuring the sequence of learning trials using neural network-based optimization can significantly improve children's ability to learn reading aloud, especially in complex spelling-sound systems like English.

Contribution

It introduces a novel neural network approach to optimize the sequence of training words, enhancing generalization in learning to read.

Findings

Significant improvement in reading accuracy with optimized sequences

Effective use of stochastic gradient descent for sequence optimization

Outperforms baseline methods like random or frequency-biased sequences

Abstract

Learning to read words aloud is a major step towards becoming a reader. Many children struggle with the task because of the inconsistencies of English spelling-sound correspondences. Curricula vary enormously in how these patterns are taught. Children are nonetheless expected to master the system in limited time (by grade 4). We used a cognitively interesting neural network architecture to examine whether the sequence of learning trials could be structured to facilitate learning. This is a hard combinatorial optimization problem even for a modest number of learning trials (e.g., 10K). We show how this sequence optimization problem can be posed as optimizing over a time varying distribution i.e., defining probability distributions over words at different steps in training. We then use stochastic gradient descent to find an optimal time-varying distribution and a corresponding optimal training sequence. We observed significant improvement on generalization accuracy compared to baseline conditions (random sequences; sequences biased by word frequency). These findings suggest an approach to improving learning outcomes in domains where performance depends on ability to generalize beyond limited training experience.