GRS: Combining Generation and Revision in Unsupervised Sentence Simplification

TL;DR

GRS is an unsupervised sentence simplification method that combines iterative revision with explicit edits and paraphrasing, improving controllability and interpretability over existing approaches.

Contribution

It introduces a novel unsupervised framework combining generation and revision with explicit edit operations and paraphrasing for sentence simplification.

Findings

Outperforms existing methods on Newsela and ASSET datasets.

Demonstrates improved controllability and interpretability.

Effectively combines generative and revision-based techniques.

Abstract

We propose GRS: an unsupervised approach to sentence simplification that combines text generation and text revision. We start with an iterative framework in which an input sentence is revised using explicit edit operations, and add paraphrasing as a new edit operation. This allows us to combine the advantages of generative and revision-based approaches: paraphrasing captures complex edit operations, and the use of explicit edit operations in an iterative manner provides controllability and interpretability. We demonstrate these advantages of GRS compared to existing methods on the Newsela and ASSET datasets.