Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification

TL;DR

This paper introduces elaborative simplification, a novel approach in text simplification that focuses on content addition and explanation, supported by a new dataset and analysis of contextual elaboration.

Contribution

It presents the first data-driven study of content addition in text simplification, including a new annotated dataset and baseline models considering contextual specificity.

Findings

Content addition can enhance explanation of complex concepts.

Considering contextual specificity improves elaboration generation.

Elaborative simplification presents new challenges and opportunities for future research.

Abstract

Much of modern-day text simplification research focuses on sentence-level simplification, transforming original, more complex sentences into simplified versions. However, adding content can often be useful when difficult concepts and reasoning need to be explained. In this work, we present the first data-driven study of content addition in text simplification, which we call elaborative simplification. We introduce a new annotated dataset of 1.3K instances of elaborative simplification in the Newsela corpus, and analyze how entities, ideas, and concepts are elaborated through the lens of contextual specificity. We establish baselines for elaboration generation using large-scale pre-trained language models, and demonstrate that considering contextual specificity during generation can improve performance. Our results illustrate the complexities of elaborative simplification, suggesting many interesting directions for future work.