GRS: Combining Generation and Revision in Unsupervised Sentence Simplification
This work addresses the problem of making text more accessible through simplification, but it is incremental as it builds on existing generative and revision-based approaches.
The authors tackled unsupervised sentence simplification by combining text generation and revision, introducing paraphrasing as an edit operation to capture complex changes while maintaining controllability and interpretability, and demonstrated advantages over existing methods on Newsela and ASSET datasets.
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.