Abstract: Systems and methods are disclosed to provide optimized scheduling of calendar events based on flexibility scores of calendar events. A flexibility score may be representative of a probability or likelihood that a calendar event can or will be rescheduled in response to a conflicting calendar event. Flexibility scores of calendar events may be calculated based on one or more factors, which may be weighted, using one or more machine-learning models. Factors may include: event densities of invitees' calendars, organizational rankings of respective invitees, the remaining time before an event start time, an urgency of respective calendar events, etc. In this way, if open time slots are not available for all invitees to a proposed calendar request, an event organizer may identify time slots occupied by existing calendar events with the highest likelihood of being rescheduled in view of the proposed calendar event, thereby facilitating scheduling of the proposed calendar event.

Abstract: Embodiments build a knowledge base that includes a list of acronyms and their expansions. The list of acronyms may be associated with a particular organization, e.g. a product team, such that the acronym may have a different meaning to a different organization. In some embodiments, acronyms and their expansions are extracted from artifacts associated with the organization, e.g. documents, emails, attachments, calendar items, etc. Multiple potential definitions identified within the artifacts may be ranked based on contextual data extracted from the artifacts, e.g. who authored the artifact, when was the artifact modified, how often did the author use the acronym, an author's rank in the organization, how long has an author been part of the organization, an author's relationship to other authors, etc. By basing the analysis on artifacts associated with the organization the resulting definitions may be more accurate than if broader resources, such as dictionary definitions, were used.

Abstract: Systems, components, devices, and methods for resolving ambiguity in a conversational understanding system are provided. A non-limiting example is a system or method for resolving ambiguity in a conversational understanding system. The method includes the steps of receiving a natural language input and identifying an agent action based on the natural language input. The method also includes the steps of determining an ambiguity value associated with the agent action and evaluating the ambiguity value against an ambiguity condition. The method includes the steps of when determined that the ambiguity value meets the ambiguity condition: selecting a prompting action based on the ambiguity associated with the identified agent action, performing the prompting action, receiving additional input in response to the prompting action, and updating the agent action to resolve the ambiguity based on the additional input. The method also includes the step of performing the agent action.

Abstract: Embodiments build a knowledge base that includes a list of acronyms and their expansions. The list of acronyms may be associated with a particular organization, e.g. a product team, such that the acronym may have a different meaning to a different organization. In some embodiments, acronyms and their expansions are extracted from artifacts associated with the organization, e.g. documents, emails, attachments, calendar items, etc. Multiple potential definitions identified within the artifacts may be ranked based on contextual data extracted from the artifacts, e.g. who authored the artifact, when was the artifact modified, how often did the author use the acronym, an author's rank in the organization, how long has an author been part of the organization, an author's relationship to other authors, etc. By basing the analysis on artifacts associated with the organization the resulting definitions may be more accurate than if broader resources, such as dictionary definitions, were used.

Abstract: Systems and methods are disclosed to provide optimized scheduling of calendar events based on flexibility scores of calendar events. A flexibility score may be representative of a probability or likelihood that a calendar event can or will be rescheduled in response to a conflicting calendar event. Flexibility scores of calendar events may be calculated based on one or more factors, which may be weighted, using one or more machine-learning models. Factors may include: event densities of invitees' calendars, organizational rankings of respective invitees, the remaining time before an event start time, an urgency of respective calendar events, etc. In this way, if open time slots are not available for all invitees to a proposed calendar request, an event organizer may identify time slots occupied by existing calendar events with the highest likelihood of being rescheduled in view of the proposed calendar event, thereby facilitating scheduling of the proposed calendar event.

Abstract: Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation based on contextual indicators. In an exemplary embodiment, email recipient recommendations may be suggested based on contextual signals, e.g., project names, body text, existing recipients, current date and time, etc. In an aspect, a plurality of properties including ranked key phrases are associated with profiles corresponding to personal entities. Aggregated profiles are analyzed using first- and second-layer processing techniques. The recommendations may be provided to the user reactively, e.g., in response to a specific query by the user to the people recommendation system, or proactively, e.g., based on the context of what the user is currently working on, in the absence of a specific query by the user.

Abstract: Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation. In an exemplary embodiment, a plurality of conversation boxes associated with communications between a user and target recipients, or between other users and recipients, are collected and stored as user history. During a training phase, the user history is used to train encoder and decoder blocks in a de-noising auto-encoder model. During a prediction phase, the trained encoder and decoder are used to predict one or more recipients for a current conversation box composed by the user, based on contextual and other signals extracted from the current conversation box. The predicted recipients are ranked using a scoring function, and the top-ranked individuals or entities may be recommended to the user.

Abstract: Systems, components, devices, and methods for resolving ambiguity in a conversational understanding system are provided. A non-limiting example is a system or method for resolving ambiguity in a conversational understanding system. The method includes the steps of receiving a natural language input and identifying an agent action based on the natural language input. The method also includes the steps of determining an ambiguity value associated with the agent action and evaluating the ambiguity value against an ambiguity condition. The method includes the steps of when determined that the ambiguity value meets the ambiguity condition: selecting a prompting action based on the ambiguity associated with the identified agent action, performing the prompting action, receiving additional input in response to the prompting action, and updating the agent action to resolve the ambiguity based on the additional input. The method also includes the step of performing the agent action.

Abstract: Systems and methods, and computer-readable media embodying the systems and methods, for responding to a search query from a computer user with diversified search results are presented. In response to a search query, a set of search results that satisfy the search query are identified. The set of search results are re-ordered according to diversity criteria associated with the requesting computer user. The diversity criteria may comprise any of a sentiment, a content source, and/or ratios thereof. One or more search results pages are generated according to the set of re-ordered search results and returned to the requesting computer user in response to the search query.

Abstract: Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation based on contextual indicators. In an exemplary embodiment, email recipient recommendations may be suggested based on contextual signals, e.g., project names, body text, existing recipients, current date and time, etc. In an aspect, a plurality of properties including ranked key phrases are associated with profiles corresponding to personal entities. Aggregated profiles are analyzed using first- and second-layer processing techniques. The recommendations may be provided to the user reactively, e.g., in response to a specific query by the user to the people recommendation system, or proactively, e.g., based on the context of what the user is currently working on, in the absence of a specific query by the user.

Abstract: Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation. In an exemplary embodiment, a plurality of conversation boxes associated with communications between a user and target recipients, or between other users and recipients, are collected and stored as user history. During a training phase, the user history is used to train encoder and decoder blocks in a de-noising auto-encoder model. During a prediction phase, the trained encoder and decoder are used to predict one or more recipients for a current conversation box composed by the user, based on contextual and other signals extracted from the current conversation box. The predicted recipients are ranked using a scoring function, and the top-ranked individuals or entities may be recommended to the user.

Abstract: Architecture that recommends (suggests) personalized and relevant documents from internal networks and/or public networks (search engines) to help the user complete/update a document currently being worked. The architecture extracts the query and uses the context to perform the search, and performs the search from within the editing application, using the entire text of the document to improve relevance. User context and textual/session context are employed to search for relevant documents. Relevant documents are proactively recommended when the user is authoring the document within an authoring application. The search operation is performed reactively using authoring context (e.g., user, textual, session, etc.) in authoring applications. Results are recommended from both internal documents (e.g., local storage, corporate network, etc.) and public documents (e.g., using a public search engine).