Microsoft Technology Licensing, LLC

Olivier Gauthier

Kaushik Ramaiah Narayanan

Michael Wilson Daniels

Domenic J Cipollone

Zhang Li

Enrico Cadoni

Alice Yingming Lai

William B Dolan

Christopher Brian Quirk

Christopher John Brockett

Kevin Roland Powell

Susan Michele Hendrich

James Cogley

Hany Grees Gerges

Siqing Chen

Maria Isabel Carpenter

Juhi Amitkumar Naik

Shashank Shekhar Gupta

Bhavuk Jain

Colin Laird

Systems and methods are directed to providing personalized text proofing. A user model that is used to personalize generic critiques for text proofing a document is generated based on user signals indicating past user actions. During runtime of an application used to create the document, the user model is accessed and locally cached. User inputs comprising typed components used to create the document are received and a set of one or more generic critiques for the user inputs is accessed from an editor system. The user model is applied to the set which may modify a generic critique of the set. The modifying of the generic critique can cause the generic critique to be automatically applied or suppressed at the client device. The set including the modified generic critique is transmitted to a user device, whereby the user device applies the set to the document including automatically applying or suppressing the modified generic critique.

Personalized text proofing using distributed services

An editor service receives a textual input. The editor service provides the textual input to a rule-based grammar checker to obtain a grammar checker result. The editor service also provides the textual input to a machine learning (ML) fluency model that checks the textual input for errors and provides a ML model result. The editor service aggregates the grammar checker result and the ML model result and generates an editor service output based upon the aggregated results. A representation of the editor service result is provided to the client computing system for surfacing through a user interface.

Using editor service to control orchestration of grammar checker and machine learned mechanism

The present disclosure relates to processing operations configured to provide, through an adapted user interface of an application/service, seamless application of autocorrection for an electronic document and provision of review insights into the autocorrections. In addition to applying autocorrections, processing described herein selectively determines when to apply an autocorrection (e.g., while a user is entering an input or after) and further highlights autocorrections, through a user interface, in a manner that instantly lets a user know that an autocorrection has occurred and/or what type of autocorrection is being applied. Moreover, an adapted user interface provides user interface features than enable access to an intelligent user interface menu that provides a user with feedback mechanisms to better understand the types of autocorrections that were made to their electronic document as well as improve processing efficiency for reversing an autocorrection and/or making further autocorrection changes to an electronic document.

Systems and methods for seamless application of autocorrection and provision of review insights through adapted user interface

A method for providing targeted rewrites can include receiving a selection of text in a file; generating a set of target rewrites of the selection of text, the set of target rewrites comprising: at least one phrase or sentence having semantic similarity to a phrase or sentence of the selection of text; and a style that corresponds to a particular target style, wherein a target style is a representative style for a genre, profession, or environment; and providing for selection one or more of the target rewrites of the set of target rewrites.

Targeted rewrites

Techniques for automatic proofing of textual data is described. In one embodiment, these techniques are directed towards producing proofed textual data for various operational environments via logic operative on a logic circuit to access information comprising a set of n-grams, at least one mapping between at least one replacement n-gram and a corresponding n-gram in the set of n-grams, and a corresponding confidence score for each mapping being determined by user activity while producing text for various applications; process input to a productivity application comprising textual data and identify a portion thereof to replace based upon the accessed information; and automatically modify the portion of the textual data using a replacement n-gram selected from the replacement n-grams based upon a corresponding confidence score between the portion of the textual data and the replacement n-gram. Other embodiments are described and claimed.

Techniques for automatic proofing of textual data

Growing community of inventors

Duvall, WA, United States of America

Olivier Gauthier