Grammarly, Inc.

In an embodiment, a computer-implemented method is executed using processors of a computer system, and includes accessing stored corpus data and tokenizing the corpus data into sequences of tokens; based on matching the sequences of tokens to a stored part-of-speech (POS) dictionary, generating a plurality of POS sequences; and accessing a first treebank data set and storing a plurality of parses from the first treebank data set in a tree data structure in a memory of the computing system. For each POS sequence, the method further includes, using the tree data structure, identifying candidate parses that matches that POS sequence; based on a stored lexical database, selecting a sentence corresponding to one candidate parse that is semantically similar to that POS sequence; substituting, in the one candidate parse, words from that POS sequence, to form an updated parse; and storing the updated parse in a second treebank data set.

A method of electronic communication assistance is provided. The method includes receiving, via an artificial intelligence assistant computing facility, an electronic communication from a first user intended to be received by a second user; and determining, via the artificial intelligence assistant computing facility, a capacity of the second user to receive the electronic communication. The method further includes determining, via the artificial intelligence assistant computing facility and based at least in part on the capacity of the second user, a time to send the electronic communication; and transmitting, via the artificial intelligence assistant computing facility, the time to the first user.

In an embodiment, a programmed computer system implemented via client-server Software as a Service (SaaS) techniques provides an interactive user interface for identifying specific portions of a digital document susceptible for review and improvement. A server computer may receive a representation of a digital document, such as an email, comprising words arranged into sentences. An embodiment may tokenize a set of all sentences comprising the sequence of sentences into a document-specific vocabulary, then compute a corresponding first and second score for each sentence of the sequence of sentences. The first score may represent a calculated probability of semantic importance of the corresponding sentence to an overall meaning of the digital document. The second score may represent a calculated likelihood that the corresponding sentence will be read by a future reader of the digital document. An embodiment may identify key sentences using the first scores and second scores.

In one embodiment, a method may receive, from a client device, a text input from a user. The text input can comprise a plurality of words. The method can access, from a server computer, common knowledge associated with a data store. The method can generate, using a generative artificial intelligence model, contextual features in a query associated with the text input. The generative artificial intelligence model has been trained to generate the contextual features in the query based on the common knowledge associated with the data store. The method can generate, using the generative artificial intelligence model, a text output using the contextual features in the query associated with the text input. The method can send, to the client device, instructions for presenting a user interface comprising the text output.

Embodiments provide a computer that includes one or more processors and instructions stored on one or more memory devices. The one or more processors executes the instructions to monitor, using one or more extractor application programming interfaces (APIs), a plurality of streams associated with user interactions with the computer, each of the plurality of streams including one or more events or activities associated with the user interactions, the user interactions being interactions with one or more different applications or platforms of the computer. The processor may extract contents and contexts from the plurality of streams using the one or more extractor APIs. The processor further determines one or more workflows associated with the user, the one or more workflows including the extracted contents and contexts, the workflows indicating the user interactions with the computer during a time series comprising a plurality of timestamps associated with times at which the user performed the interactions with the computer. The processor stores the one or more the workflows at the user computer. The processor determines one or more chunks of the one or more workflows, each chunk being a subpart of one of the one or more workflows and corresponding to a set of the plurality of timestamps associated with the subpart, each chunk including the content and contexts of the one or more workflows associated with the set of the plurality of timestamps. The processors evaluates the one or more chunks, the evaluating creating one or more inferred actions using the content and contexts of the one or more workflows associated with the set of the plurality of timestamps and automates one or more subsequent workflows associated with the user based on the one or more inferred actions.

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.

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.

A computer-implemented process is programmed to programmatically receive at a first computer a digital electronic object including a source text that is directed to a target audience and that was composed at a second computer, determine a style value specifying a particular communication style from among different communication styles based on a communication profile of the target audience, evaluate the source text using a trained machine-learning model, receive a classification output from the machine-learning model, generate an output set of suggested edits to the source text based on comparing the classification output to the source text, and transmit the output set of suggested edits to the second computer. The classification output from the machine-learning model includes a modified text based on the source text. The modified text has been classified using the particular communication style specified in the style value.

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.