Abstract: A method and system for providing replacement text segments for a given text segment may include receiving a request to provide the replacement text segment for the text segment in the document, examining a content characteristic of the document, and examining at least one of user-specific information, organization-specific information, or non-linguistic features of the document, before identifying at least one replacement text segment for the text segment, via a machine translation system, based on the content characteristic of the document and at least one of the user-specific information, the organization-specific information, or the non-linguistic features of the document. The method and system may include providing the identified replacement text segment for display to a user, receiving an input indicating a user's selection of the identified replacement text segment, and upon receiving the input, replacing the text segment in the document with the identified replacement text segment.

Abstract: A method and system for providing tone detection and modification for a content segment may include receiving a request to detect a tone for the content segment, inputting the content segment into a first machine-learning (ML) model to detect the tone for the content segment, obtaining the detected tone as a first output from the first ML model, inputting the content segment into a second ML model for modifying the tone from the detected tone to a modified tone, obtaining at least one rephrased content segment as a second output from the second ML model, the rephrased content segment modifying the tone of the content segment from the detected tone to the modified tone, and providing at least one of the detected tone or the at least one rephrased content segment for display to a user.

Abstract: The present disclosure relates to processing operations configured to tailor notifications of productivity feature suggestions based on predictive relevance to a context associate with user access to an electronic document. Machine learning modeling executes a contextual evaluation of user access to predictively determine relevance of a suggestion that relates to: 1) a confidence in the quality of the suggestion; and 2) a timing prediction as to the urgency for surfacing the suggestion to the user so that the suggestion is most applicable. Example notifications are proactive interruptions that aim to aid processing efficiency in task execution as well as an improve user interface experience when users work with an application/service and/or an application platform that comprises a suite of applications/services. A manner in which the notification is presented may vary based on the confidence in the relevance of the suggestion and timing relevance for interrupting a user's workflow.

Abstract: 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.

Abstract: The present disclosure relates to processing operations configured to identify and present productivity features that are contextually relevant for user access to an electronic document. In doing so, signal data is evaluated to determine a context associated with user access to an electronic document and insights, from the determined context, are utilized to rank productivity features for relevance to a user workflow. As an example, an intelligent learning model is trained and implemented to identify what productivity features are most relevant to a current task of a user. Productivity features are identified and ranked for contextual relevance. A notification comprising one or more ranked productivity features is presented to a user. In one example, the notification is presented through a user interface of an application/service. For instance, a user interface pane is surfaced to present suggestions.

Abstract: A method and system for providing replacement text segments for a given text segment may include receiving a request to provide the replacement text segment for the text segment in the document, examining a content characteristic of the document, and examining at least one of user-specific information, organization-specific information, or non-linguistic features of the document, before identifying at least one replacement text segment for the text segment, via a machine translation system, based on the content characteristic of the document and at least one of the user-specific information, the organization-specific information, or the non-linguistic features of the document. The method and system may include providing the identified replacement text segment for display to a user, receiving an input indicating a user's selection of the identified replacement text segment, and upon receiving the input, replacing the text segment in the document with the identified replacement text segment.

Abstract: 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.

Abstract: The present disclosure relates to processing operations configured to identify and present productivity features that are contextually relevant for user access to an electronic document. In doing so, signal data is evaluated to determine a context associated with user access to an electronic document and insights, from the determined context, are utilized to rank productivity features for relevance to a user workflow. As an example, an intelligent learning model is trained and implemented to identify what productivity features are most relevant to a current task of a user. Productivity features are identified and ranked for contextual relevance. A notification comprising one or more ranked productivity features is presented to a user. In one example, the notification is presented through a user interface of an application/service. For instance, a user interface pane is surfaced to present suggestions.

Abstract: The present disclosure relates to processing operations configured to tailor notifications of productivity feature suggestions based on predictive relevance to a context associate with user access to an electronic document. Machine learning modeling executes a contextual evaluation of user access to predictively determine relevance of a suggestion that relates to: 1) a confidence in the quality of the suggestion; and 2) a timing prediction as to the urgency for surfacing the suggestion to the user so that the suggestion is most applicable. Example notifications are proactive interruptions that aim to aid processing efficiency in task execution as well as an improve user interface experience when users work with an application/service and/or an application platform that comprises a suite of applications/services. A manner in which the notification is presented may vary based on the confidence in the relevance of the suggestion and timing relevance for interrupting a user's workflow.

Abstract: A method for displaying an information collection includes collecting a plurality of user signals associated with a user of a device, and identifying a first subject from the plurality of user signals. The first subject has at least a first piece of information. A connection between the first subject and a second subject is determined, and a second piece of information from the second subject is determined. The second piece of information is relevant to the first piece of information. The first and second pieces of information are assembled into a user information collection.