Improving Iterative Text Revision by Learning Where to Edit from Other Revision Tasks

TL;DR

This paper presents an end-to-end system for iterative text revision that detects editable spans and their intents to improve various text editing tasks, outperforming previous methods.

Contribution

It introduces a novel approach that explicitly models where and how to edit in iterative revisions, leveraging datasets from related NLP tasks for better accuracy.

Findings

Significant improvement over baselines in multiple text revision tasks

Effective detection of editable spans and edit intents

Enhanced understanding of the link between edit intentions and writing quality

Abstract

Iterative text revision improves text quality by fixing grammatical errors, rephrasing for better readability or contextual appropriateness, or reorganizing sentence structures throughout a document. Most recent research has focused on understanding and classifying different types of edits in the iterative revision process from human-written text instead of building accurate and robust systems for iterative text revision. In this work, we aim to build an end-to-end text revision system that can iteratively generate helpful edits by explicitly detecting editable spans (where-to-edit) with their corresponding edit intents and then instructing a revision model to revise the detected edit spans. Leveraging datasets from other related text editing NLP tasks, combined with the specification of editable spans, leads our system to more accurately model the process of iterative text refinement, as evidenced by empirical results and human evaluations. Our system significantly outperforms previous baselines on our text revision tasks and other standard text revision tasks, including grammatical error correction, text simplification, sentence fusion, and style transfer. Through extensive qualitative and quantitative analysis, we make vital connections between edit intentions and writing quality, and better computational modeling of iterative text revisions.