Text revision in Scientific Writing Assistance: An Overview
Léane Jourdan, Florian Boudin, Richard Dufour, Nicolas Hernandez
TL;DR
The paper surveys text revision in scientific writing assistance (SWA), focusing on NLP-based tools that improve draft content and phrasing in scientific articles. It defines the revision task, surveys the IMRaD structure and argumentative modeling (e.g., CARS and AZ frameworks), and catalogs a range of tools categorized into sentence revision, grammar checkers, and move annotators. Notable systems discussed include Langsmith, R3, ChatGPT, Grammarly, LinggleWrite, Mover, RWT, and AcaWriter, illustrating a spectrum from automated edits to discourse-aware feedback. The authors identify key challenges—benchmarking across tools, incorporating larger textual context, applying discourse and argumentation analyses, data availability, accessibility, transparency, and ethical issues—offering a roadmap for advancing SWA in scientific writing.
Abstract
Writing a scientific article is a challenging task as it is a highly codified genre. Good writing skills are essential to properly convey ideas and results of research work. Since the majority of scientific articles are currently written in English, this exercise is all the more difficult for non-native English speakers as they additionally have to face language issues. This article aims to provide an overview of text revision in writing assistance in the scientific domain. We will examine the specificities of scientific writing, including the format and conventions commonly used in research articles. Additionally, this overview will explore the various types of writing assistance tools available for text revision. Despite the evolution of the technology behind these tools through the years, from rule-based approaches to deep neural-based ones, challenges still exist (tools' accessibility, limited consideration of the context, inexplicit use of discursive information, etc.)