Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision

Wanyu Du, Zae Myung Kim, Vipul Raheja, Dhruv Kumar, Dongyeop Kang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Revision is an essential part of the human writing process. It tends to be strategic, adaptive, and, more importantly, iterative in nature. Despite the success of large language models on text revision tasks, they are limited to non-iterative, one-shot revisions. Examining and evaluating the capability of large language models for making continuous revisions and collaborating with human writers is a critical step towards building effective writing assistants. In this work, we present a human-in-the-loop iterative text revision system, Read, Revise, Repeat (R3), which aims at achieving high quality text revisions with minimal human efforts by reading model-generated revisions and user feedbacks, revising documents, and repeating human-machine interactions. In R3, a text revision model provides text editing suggestions for human writers, who can accept or reject the suggested edits. The accepted edits are then incorporated into the model for the next iteration of document revision. Writers can therefore revise documents iteratively by interacting with the system and simply accepting/rejecting its suggested edits until the text revision model stops making further revisions or reaches a predefined maximum number of revisions. Empirical experiments show that R3 can generate revisions with comparable acceptance rate to human writers at early revision depths, and the human-machine interaction can get higher quality revisions with fewer iterations and edits. The collected human-model interaction dataset and system code are available at https://github.com/vipulraheja/IteraTeR. Our system demonstration is available at https://youtu.be/lK08tIpEoaE.

Original languageEnglish (US)
Title of host publicationIn2Writing 2022 - 1st Workshop on Intelligent and Interactive Writing Assistants, Proceedings of the Workshop
EditorsTing-Hao Huang, Vipul Raheja, Dongyeop Kang, John Joon Young Chung, Daniel Gissin, Mina Lee, Katy Ilonka Gero
PublisherAssociation for Computational Linguistics (ACL)
Pages96-108
Number of pages13
ISBN (Electronic)9781955917391
StatePublished - 2022
Event1st Workshop on Intelligent and Interactive Writing Assistants, In2Writing 2022 - Dublin, Ireland
Duration: May 26 2022 → …

Publication series

NameIn2Writing 2022 - 1st Workshop on Intelligent and Interactive Writing Assistants, Proceedings of the Workshop

Conference

Conference1st Workshop on Intelligent and Interactive Writing Assistants, In2Writing 2022
Country/TerritoryIreland
CityDublin
Period5/26/22 → …

Bibliographical note

Funding Information:
We thank all linguistic expert annotators at Grammarly for participating in the user study and providing us with valuable feedback during the process. We also thank Karin de Langis at University of Minnesota for narrating the video of our system demonstration. We would like to extend our gratitude to the anonymous reviewers for their helpful comments.

Publisher Copyright:
©2022 Association for Computational Linguistics.

Fingerprint

Dive into the research topics of 'Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision'. Together they form a unique fingerprint.

Cite this