Context-Preserving Text Simplification

TL;DR

This paper introduces a context-preserving text simplification method that recursively splits complex sentences into a semantic hierarchy, maintaining discourse relations and improving interpretability.

Contribution

It presents a novel hierarchical sentence splitting approach that preserves discourse-level context, unlike previous methods that ignore semantic relationships.

Findings

Achieved 89% precision in capturing contextual hierarchy.

Reached 69% average precision in classifying rhetorical relations.

Demonstrated improved semantic preservation over existing approaches.

Abstract

We present a context-preserving text simplification (TS) approach that recursively splits and rephrases complex English sentences into a semantic hierarchy of simplified sentences. Using a set of linguistically principled transformation patterns, input sentences are converted into a hierarchical representation in the form of core sentences and accompanying contexts that are linked via rhetorical relations. Hence, as opposed to previously proposed sentence splitting approaches, which commonly do not take into account discourse-level aspects, our TS approach preserves the semantic relationship of the decomposed constituents in the output. A comparative analysis with the annotations contained in the RST-DT shows that we are able to capture the contextual hierarchy between the split sentences with a precision of 89% and reach an average precision of 69% for the classification of the rhetorical relations that hold between them.