Grammarly, Inc.

In an embodiment, the disclosed technologies are capable of receiving, by a digital model, data representing a first text sequence in a first language; using the digital model, modifying the first text sequence to result in creating and digitally storing a second text sequence in the first language; and outputting, by the digital model, the second text sequence in the first language. The modifying may include any one or more of: deleting text from the first text sequence, adding text to the first text sequence, modifying text of the first text sequence, reordering text of the first text sequence, adding a digital markup to the first text sequence. The digital model may have been fine-tuned, after having been machine-learned, using a subset of values of model parameters associated with an encoding layer or an embedding layer or both the encoding layer and the embedding layer.

In an embodiment, the disclosed technologies are capable of receiving, by a digital model, data representing a first text sequence in a first language; using the digital model, modifying the first text sequence to result in creating and digitally storing a second text sequence in the first language; and outputting, by the digital model, the second text sequence in the first language. The modifying may include any one or more of: deleting text from the first text sequence, adding text to the first text sequence, modifying text of the first text sequence, reordering text of the first text sequence, adding a digital markup to the first text sequence. The digital model may have been fine-tuned, after having been machine-learned, using a subset of values of model parameters associated with an encoding layer or an embedding layer or both the encoding layer and the embedding layer.

In one embodiment, the disclosure provides a computer-implemented method, comprising receiving, by a computer system, electronic digital data representing a first text sequence in a first language, the first text sequence comprising unstructured natural language text; by one or more machine-learning models of the computer system, determining a score corresponding to the first text sequence, the score being determined by one or more rule-based filters and indicating one or more predicted tones; determining whether to modify the first text sequence based on the score of the first text sequence; in response to a determination to modify the first text sequence, modifying the first text sequence, the modifying comprising replacement of at least one or more words of the first text sequence to result in creating and digitally storing a second text sequence; and transmitting a graphical control element indicative of a tone associated with the second text sequence for display.

In one embodiment, a method receives, by a computing device, a text change in a text entry which includes one or more text units. The method may access, using a data store, a record associated with a user identifier which includes one or more top N similar hash values associated with the user identifier. The method may determine one or more hash values by applying a hash function over the one or more text units of the text change. The method may compare each of the one or more hash values to the one or more top N similar hash values. In response to determining a match between at least one of the one or more hash values and the one or more top N similar hash values, the method may determine a phrase suggestion using the text change to visually present on the computing device.

Systems and methods include interpreting a first user input from a first user, the first user input comprising a text flow entry, interpreting a second user input from the first user, the second user input comprising at least one of: an in-line data access entry or a table-based calculation entry, positioning a text entry value on a unified document surface in response to the first user input, creating at least one data structure in response to the second user input, the at least one data structure comprising data from an external data source, the external data source being external to the unified document surface, and positioning the at least one data structure on the unified document surface.

The present disclosure describes methods and systems for interpreting a first user input comprising a text flow entry, interpreting a second user input comprising one of an in-line data access entry and a table-based calculation entry, positioning a text entry value on a unified document surface in response to the first user input, creating at least one data structure in response to the one of the in-line data access entry and the table-based calculation entry, and positioning the data structure on the unified document surface.

A computer-implemented process is programmed to programmatically receive, using a first computer system, electronic digital data representing input time-correlated speech data and video data, determine a first text sequence corresponding to the input time-correlated speech data, the first text sequence comprising unstructured natural language text, determining syntactic structure data associated with the first text sequence, inputting the time-correlated video data and the syntactic structure data associated with the first text sequence into one or more machine learning models, the machine learning models producing an output of one or more scores for at least a portion of the time-correlated video data and first text sequence, transforming the output of one or more scores to yield and output set of summary points and suggestions, and transmitting a graphical element of the output set of summary points and suggestions for display.

An example system may include a document snapshot circuit structured to generate a document snapshot configured to capture a state of a document at a time marker and a document sharding circuit structured to analyze the document snapshot, and generate a first plurality of shard documents capturing the state of the document at the time marker. The system may include a document serving circuit structured to access the first plurality of shard documents, and provide at least a subset of the first plurality of shard documents to a client serving circuit structured to implement a unified document surface interface in response to the at least a subset of the first plurality of shard documents. The document serving circuit is configured to provide the subset of the first plurality of shard documents in an order determined to prioritize shards related to a last accessed location of the document.

In an embodiment, the disclosed technologies are capable of detecting a tone in text. A detected tone may be used to inform a decision made by and/or output produced by a grammatical error correction system. A set of candidate tones may be presented to a user for feedback. User feedback on the candidate tones may be used to improve subsequent tone detections.

In an embodiment, a computer-implemented method is executed using processors of a computer system, and includes receiving a copy of a stored digital image comprising a screen capture of an application window displayed on the computing device while the computing device accesses or executes a videoconferencing application. The computer-implemented method includes executing an optical character recognition (OCR) process on the screen capture of the application window to identify natural language text characters included within the set of digital images, determining, based on the identified text characters, a set of information associated with text characters of the identified text characters, programmatically transmitting instructions for displaying components that can overlay the videoconferencing application executing on the computing device, programmatically instructing the computing device to redisplay the application window along with the components overlaying the videoconferencing application, such that the text characters are displayed as emphasized within the set of digital images.