AutoMeTS: The Autocomplete for Medical Text Simplification

TL;DR

This paper explores using pretrained neural language models to assist in medical text simplification, creating a semi-automated tool that improves the speed and quality of simplifying complex medical texts for broader accessibility.

Contribution

It introduces a new aligned medical dataset and demonstrates how combining multiple pretrained models enhances text simplification accuracy.

Findings

Ensemble model outperforms individual models by 2.1%.

Sentence context improves model performance by 6.17%.

Achieved 64.52% word prediction accuracy.

Abstract

The goal of text simplification (TS) is to transform difficult text into a version that is easier to understand and more broadly accessible to a wide variety of readers. In some domains, such as healthcare, fully automated approaches cannot be used since information must be accurately preserved. Instead, semi-automated approaches can be used that assist a human writer in simplifying text faster and at a higher quality. In this paper, we examine the application of autocomplete to text simplification in the medical domain. We introduce a new parallel medical data set consisting of aligned English Wikipedia with Simple English Wikipedia sentences and examine the application of pretrained neural language models (PNLMs) on this dataset. We compare four PNLMs(BERT, RoBERTa, XLNet, and GPT-2), and show how the additional context of the sentence to be simplified can be incorporated to achieve better results (6.17% absolute improvement over the best individual model). We also introduce an ensemble model that combines the four PNLMs and outperforms the best individual model by 2.1%, resulting in an overall word prediction accuracy of 64.52%.