Microsoft Technology Licensing, LLC

Jesse Alexander Freitas

Zhang Li

Warren Anthony Aldred

Si-Qing Chen

William B Dolan

Christopher John Brockett

Tomasz Lukasz Religa

Kaushik Ramaiah Narayanan

Michel Galley

Max Wang

Huitian Jiao

Siqing Chen

Xun Wang

Alyssa Rachel Mayo

Mahaveer Bhavarlal Kothari

Tao Ge

Christine Lauren Mayer

Tashfeen Ahmed

Cheng Yang

Bhavuk Jain

Xinyu He

Utkarsh Garg

Aleksey Aleksandrovich Sokolov

Saket Kumar

Olivier Michel Nicolas Gauthier

Weixin Cai

A data processing system obtains source textual content associated with a first writing style and target textual content associated with a second writing style and provides the source textual content as an input to a first machine learning model which analyzes the source content to determine the first writing style of the first textual content. The system provides an indication of the first writing style and the target textual content as an input to a second machine learning model which analyzes the target textual content and rewrites the target textual content according to the first writing style to output updated target textual content rewritten according to the first writing style. Some implementations utilize a single model trained to receive the source textual content, the target textual content, to determine the writing style of the source textual content and rewrite the target textual content according to the first writing style.

Automatic writing style detection and rewriting

A data processing system includes: a processor; a memory containing programming instructions for execution by the processor; and a network interface for communicating with an Artificial Intelligence (AI) engine. The programming instructions include an application for generating written content, the application having a function to generate and submit a structured query regarding the written content to the AI engine to generate feedback on an assessed quality of the written content, the structured query structured to prompt for feedback in a variety of specified categories for the written content. The application further includes a user interface to display the feedback on the written content and provide an option to a user to implement the feedback to revise the written content.

Systems and methods for writing feedback using an artificial intelligence engine

Systems and methods are directed to generating content that is contextually relevant in a writing style of a user. In example embodiments, a plurality of logical inputs regarding a topic is received in bullet point format. A content generator generates draft content using machine learning (ML) models. The generating comprises identifying a writing style of the user by applying the plurality of logical inputs to a first ML model, determining a context and direction for the draft content using a second ML model, and based on the plurality of logical inputs, the identified writing style, and the context and direction, generating at least one paragraph of draft content in the writing style of the user that follows an outline associated with the bullet point format and comprises a same context and direction as the plurality of logical inputs. The draft content is then presented at a client device.

Automatic content generation

A method and system for providing improper reference identification for a content segment may include receiving a request to identify an improper reference in the content segment, inputting the content segment into a machine-learning (ML) model to identify the improper reference in the content segment, obtaining the identified improper reference as a first output from the ML model, obtaining one or more suggested replacement references as a second output from the ML model, and providing at least one of the identified improper reference or the at least one of the one or more suggested replacements for display.

Intelligent identification and modification of references in content

Growing community of inventors

Seattle, WA, United States of America

Jesse Alexander Freitas