Noisy Channel for Automatic Text Simplification
This work addresses a known limitation in end-to-end neural models for text simplification, offering a way to control important aspects of the output, though it is incremental in nature.
The paper tackles the problem of automatic text simplification by introducing a noisy channel-based re-ranking method that considers both the probability of generating the complex text from the simple one and the probability of the simple text itself, outperforming the original system across three English datasets and achieving the best known result in one.
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.