Automating Easy Read Text Segmentation

TL;DR

This paper explores automated methods for segmenting Easy Read text to improve accessibility for people with reading difficulties, using language models and parsing across multiple languages, showing promising results but still some gaps compared to human segmentation.

Contribution

It introduces novel automated segmentation techniques leveraging language models and parsing, evaluated across languages and resource constraints, demonstrating their potential for Easy Read content creation.

Findings

Automated segmentation is viable but still lags behind human performance.

Language models and parsing improve segmentation quality.

Cross-lingual evaluation shows consistent strengths and weaknesses.

Abstract

Easy Read text is one of the main forms of access to information for people with reading difficulties. One of the key characteristics of this type of text is the requirement to split sentences into smaller grammatical segments, to facilitate reading. Automated segmentation methods could foster the creation of Easy Read content, but their viability has yet to be addressed. In this work, we study novel methods for the task, leveraging masked and generative language models, along with constituent parsing. We conduct comprehensive automatic and human evaluations in three languages, analysing the strengths and weaknesses of the proposed alternatives, under scarce resource limitations. Our results highlight the viability of automated Easy Read text segmentation and remaining deficiencies compared to expert-driven human segmentation.