Grammarly, Inc.

Roman Guliak

Stanislav Levental

Yuriy Tanskiy

Valentyn Gaidylo

Yura Tanskiy

Victor Pavlychko

Nikita Volobuiev

Ievgen Rysai

Oleksiy Shevchenko

In one embodiment, the disclosure provides a computer-implemented or programmed method, comprising: causing subscribing to a plurality of events provided by a first application programming interface; receiving a layout change event pushed from the first application programming interface; determining that a change in focused element resulted in a currently focused element; causing generating a transparent window on top of the currently focused element; causing receiving one or more character ranges respectively associated with one or more types of markup; causing determining one or more screen bounds corresponding to the one or more character ranges; and, causing respectively displaying, in the transparent window, the one or more types of markup at the screen bounds corresponding to the one or more character ranges associated with that type of markup.

Inferred event detection and text processing using transparent windows

In an embodiment, the disclosed technologies are capable of identifying a target word within a text sequence; displaying a subset of candidate synonyms for the target word, determining a synonym selected from the subset of candidate synonyms, and replacing the target word with the selected synonym, where the subset of candidate synonyms has been created using syntactic dependency data for the target word.

Computer-implemented presentation of synonyms based on syntactic dependency

In one embodiment, the disclosure provides a computer-implemented or programmed method, comprising: causing subscribing to a plurality of events provided by a first application programming interface; receiving a layout change event pushed from the first application programming interface; determining that a change in focused element resulted in a currently focused element; receiving, from the currently focused element, a digital electronic object comprising a source text; programmatically dividing the source text into a plurality of source text units; programmatically evaluating each particular source text unit among the plurality of source text units using a machine learning model, and receiving a classification output from the machine learning model; programmatically transforming the classification output to yield an output set of phrase suggestions; and, causing displaying one or more phrase suggestions of the output set of phrase suggestions.

Growing community of inventors

San Francisco, CA, United States of America

Roman Guliak