Iterative Edit-Based Unsupervised Sentence Simplification

TL;DR

This paper introduces an unsupervised, iterative sentence simplification method that uses a scoring function to guide edits, achieving competitive results without needing parallel training data.

Contribution

The novel approach performs iterative, edit-based simplification guided by a scoring function, eliminating the need for parallel datasets and enhancing interpretability.

Findings

Nearly matches state-of-the-art supervised methods

Effective on Newsela and WikiLarge datasets

More controllable and interpretable than previous models

Abstract

We present a novel iterative, edit-based approach to unsupervised sentence simplification. Our model is guided by a scoring function involving fluency, simplicity, and meaning preservation. Then, we iteratively perform word and phrase-level edits on the complex sentence. Compared with previous approaches, our model does not require a parallel training set, but is more controllable and interpretable. Experiments on Newsela and WikiLarge datasets show that our approach is nearly as effective as state-of-the-art supervised approaches.