Abstract: A system for handling errors during automatic speech recognition by processing a potentially defective utterance to determine an alternative, potentially successful utterance. The system processes the N-best ASR hypotheses corresponding to the defective utterance using a trained model to generate a word-level feature vector. The word-level feature vector is processed using a sequence-to-sequence architecture to determine the alternate utterance.

Abstract: Techniques for decreasing (or eliminating) the possibility of a skill performing an action that is not responsive to a corresponding user input are described. A system may train one or more machine learning models with respect to user inputs, which resulted in incorrect actions being performed by skills, and corresponding user inputs, which resulted in the correct action being performed. The system may use the trained machine learning model(s) to rewrite user inputs that, if not rewritten, may result in incorrect actions being performed. The system may implement the trained machine learning model(s) with respect to ASR output text data to determine if the ASR output text data corresponds (or substantially corresponds) to previous ASR output text data that resulted in an incorrect action being performed.

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: Described herein are systems and methods for scheduling a resource that is shared by multiple people. The shared resource is included in a plurality of shared resources, and a number of attributes are associated with the plurality of shared resources. The attributes are grouped and arranged in a hierarchy. When a shared resource is to be used or scheduled, the hierarchy is analyzed to determine one or more shared resources in the plurality of shared resources to suggest to a requestor scheduling the shared resource.

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: A search engine is described herein for providing search results based on a context in which a query has been submitted, as expressed by context information. The search engine operates by ranking a plurality of documents based on a consideration of the query, and based, in part, on a context concept vector and a plurality of document concept vectors, both generated using a deep learning model (such as a deep neural network). The context concept vector is formed by a projection of the context information into a semantic space using the deep learning model. Each document concept vector is formed by a projection of document information, associated with a particular document, into the same semantic space using the deep learning model. The ranking operates by favoring documents that are relevant to the context within the semantic space, and disfavoring documents that are not relevant to the context.

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).

Abstract: Architecture that utilizes server-based signals (e.g., past engagement, application popularity, spell-correction, mined search patterns, machine learning models, etc.) to improve relevance of search results for local applications and settings. The architecture works for any operating system (OS) and any client device that has local settings or applications installed. The architecture also covers instances where server-signals are being used to improve queries on devices where settings are searched but no applications are installed or will not be installed.

Abstract: A search engine is described herein for providing search results based on a context in which a query has been submitted, as expressed by context information. The search engine operates by ranking a plurality of documents based on a consideration of the query, and based, in part, on a context concept vector and a plurality of document concept vectors, both generated using a deep learning model (such as a deep neural network). The context concept vector is formed by a projection of the context information into a semantic space using the deep learning model. Each document concept vector is formed by a projection of document information, associated with a particular document, into the same semantic space using the deep learning model. The ranking operates by favoring documents that are relevant to the context within the semantic space, and disfavoring documents that are not relevant to the context.

Abstract: Distributed and local processes analyze usage data and transform it into objects including timestamps and dimensions. Objects include a position vector to represent dimension analysis and additional attributes associated with measurements of different types. The objects are stored in a multidimensional database indexed on the vector and timestamp attributes.

Abstract: Distributed and local processes analyze usage data and transform it into objects including timestamps and dimensions. Objects include a position vector to represent dimension analysis and additional attributes associated with measurements of different types. The objects are stored in a multidimensional database indexed on the vector and timestamp attributes.