Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text

TL;DR

This paper introduces KiS, an unsupervised method for multi-paragraph text simplification that balances fluency, salience, and simplicity, improving comprehension speed and outperforming supervised baselines.

Contribution

The paper presents a novel unsupervised training algorithm (k-SCST) and a realistic evaluation method for text simplification, demonstrating significant improvements over supervised models.

Findings

KiS outperforms supervised baselines by over 4 SARI points.

Participants completed comprehension tasks 18% faster with KiS.

The approach effectively balances multiple properties in text simplification.

Abstract

This work presents Keep it Simple (KiS), a new approach to unsupervised text simplification which learns to balance a reward across three properties: fluency, salience and simplicity. We train the model with a novel algorithm to optimize the reward (k-SCST), in which the model proposes several candidate simplifications, computes each candidate's reward, and encourages candidates that outperform the mean reward. Finally, we propose a realistic text comprehension task as an evaluation method for text simplification. When tested on the English news domain, the KiS model outperforms strong supervised baselines by more than 4 SARI points, and can help people complete a comprehension task an average of 18% faster while retaining accuracy, when compared to the original text. Code available: https://github.com/tingofurro/keep_it_simple