Noisy Channel for Automatic Text Simplification

TL;DR

This paper introduces a re-ranking method for automatic sentence simplification using a noisy channel approach, which improves performance by considering probabilities of both complex and simple sentences, surpassing previous systems.

Contribution

The paper proposes a novel re-ranking approach based on the noisy channel scheme for automatic text simplification, enhancing control and performance over existing end-to-end models.

Findings

Outperforms previous simplification systems on three datasets

Achieves best known results in one dataset

Demonstrates the effectiveness of noisy channel re-ranking

Abstract

In this paper we present a simple re-ranking method for Automatic Sentence Simplification based on the noisy channel scheme. Instead of directly computing the best simplification given a complex text, the re-ranking method also considers the probability of the simple sentence to produce the complex counterpart, as well as the probability of the simple text itself, according to a language model. Our experiments show that combining these scores outperform the original system in three different English datasets, yielding the best known result in one of them. Adopting the noisy channel scheme opens new ways to infuse additional information into ATS systems, and thus to control important aspects of them, a known limitation of end-to-end neural seq2seq generative models.