Proofreader API

[QueenieZqq]

Introduction

Proofreading is the process of examining a text carefully to find and correct errors such as grammar, spelling, and punctuation to generate an error-free text before it is published or shared. Browsers and operating systems are increasingly offering proofreading capability to help their users compose (examples: Example, Example). Web applications can also benefit from such proofreading capability backed by language models for a variety of use cases.

We're proposing an API that uses language models to give web developers high-level functionalities for proofreading. Specifically:

1. Error Correction: Correct input text by the user
2. Error Labeling: For each correction made to each error in the input text, label the error type (e.g. spelling, punctuation, etc.)
3. Error Explanation: Annotates each error with a plain language explanation

Read the complete Explainer.

Feedback

We welcome feedback in this thread, but encourage you to file bugs against the Explainer.

[domenic]

Some notes:

• We discussed this among the Web ML Community Group on https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-03-12-cg-minutes.md#proofreader-api
• It's possible this might fit well under the "Writing Assistance APIs" banner, hosted at https://github.com/WICG/writing-assistance-apis/ . Although, it is different from those in some ways, e.g. in having a more structured output. So, I am not sure what structure is best for organizing the specifications.

[anssiko]

This API is now proposed to be added to the WebML CG: https://lists.w3.org/Archives/Public/public-webmachinelearning/2025Apr/0001.html

This gives us flexibility to organize the API either as a standalone spec or fold into an existing API spec.