Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: Because digital assistants tend to have different areas of expertise and/or different abilities to fulfill a given request, it is sometimes difficult for a user to know which digital assistant is best able to fulfill a request. Representative embodiments disclose mechanisms to increase federate digital assistants so that a user's request can be funneled to the digital assistant best able to fulfill the user's request. A meta-assistant gathers information on skills provided by a set of digital assistants. The meta-assistant also gathers completion data for requests for different digital assistants and user satisfaction information. A user submits a request to the meta-assistant. The meta-assistant extracts user intent from the request and redirects the user's request to the digital assistant best able to fulfill the request. Embodiments can utilize trained machine learning models or scored algorithmic approaches to select the digital assistant.

Abstract: Systems and methods are provided for automatically controlling a participant indication request based on a context of a meeting. The controlling of the participant indication request includes automatic lowering of a raised hand. A context determiner determines the context of the meeting based on meeting data including video, audio, background acoustic data, and chat messaging. The context determiner uses a global participant indication model for determining a context that is in commonly used among participants of the meeting. An individual participant indication model captures participant-specific rules of determining a context. A meeting state manager determines a meeting state based on the context. The meeting state includes a host presentation, a participant presentation, a conversation, and a polling. A participant indication controller automatically lowers the raised hand based on a combination of the determined context and the meeting state.

Abstract: Disclosed are techniques for extracting, identifying, and consuming imprecise temporal elements (“ITEs”). A user input may be received from a client device. A prediction may be generated of one or more time intervals to which the user input refers based upon an ITE model. The user input may be associated with the prediction, and provided to the client device.

Abstract: Systems and methods are provided for automatically controlling a participant indication request based on a context of a meeting. The controlling of the participant indication request includes automatic lowering of a raised hand. A context determiner determines the context of the meeting based on meeting data including video, audio, background acoustic data, and chat messaging. The context determiner uses a global participant indication model for determining a context that is in commonly used among participants of the meeting. An individual participant indication model captures participant-specific rules of determining a context. A meeting state manager determines a meeting state based on the context. The meeting state includes a host presentation, a participant presentation, a conversation, and a polling. A participant indication controller automatically lowers the raised hand based on a combination of the determined context and the meeting state.

Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: Systems and methods are provided for automatically controlling a participant indication request based on a context of a meeting. The controlling of the participant indication request includes automatic lowering of a raised hand. A context determiner determines the context of the meeting based on meeting data including video, audio, background acoustic data, and chat messaging. The context determiner uses a global participant indication model for determining a context that is in commonly used among participants of the meeting. An individual participant indication model captures participant-specific rules of determining a context. A meeting state manager determines a meeting state based on the context. The meeting state includes a host presentation, a participant presentation, a conversation, and a polling. A participant indication controller automatically lowers the raised hand based on a combination of the determined context and the meeting state.

Abstract: Disclosed are techniques for extracting, identifying, and consuming imprecise temporal elements (“ITEs”). A user input may be received from a client device. A prediction may be generated of one or more time intervals to which the user input refers based upon an ITE model. The user input may be associated with the prediction, and provided to the client device.

Abstract: Disclosed are techniques for extracting, identifying, and consuming imprecise temporal elements (“ITEs”). A user input may be received from a client device. A prediction may be generated of one or more time intervals to which the user input refers based upon an ITE model. The user input may be associated with the prediction, and provided to the client device.

Abstract: Representative embodiments disclose mechanisms to map natural language input to an application programming interface (API) call. The natural language input is first mapped to an API frame, which is a representation of the API call without any API call formatting. The mapping from natural language input to API frame is performed using a trained sequence to sequence neural model. The sequence to sequence neural model is decomposed into small prediction units called modules. Each module is highly specialized at predicting a pre-defined kind of sequence output. The output of the modules can be displayed in an interactive user interface that allows the user to add, remove, and/or modify the output of the individual modules. The user input can be used as further training data. The API frame is mapped to an API call using a deterministic mapping.

Abstract: Because digital assistants tend to have different areas of expertise and/or different abilities to fulfill a given request, it is sometimes difficult for a user to know which digital assistant is best able to fulfill a request. Representative embodiments disclose mechanisms to increase federate digital assistants so that a user's request can be funneled to the digital assistant best able to fulfill the user's request. A meta-assistant gathers information on skills provided by a set of digital assistants. The meta-assistant also gathers completion data for requests for different digital assistants and user satisfaction information. A user submits a request to the meta-assistant. The meta-assistant extracts user intent from the request and redirects the user's request to the digital assistant best able to fulfill the request. Embodiments can utilized trained machine learning models or scored algorithmic approaches to select the digital assistant.

Abstract: Various technologies pertaining to exploratory suggestions are described herein. A computer-implemented graph is constructed, where the graph includes nodes that are representative of aspects and edges that are representative of associations between aspects. An aspect is representative of a sub-topic of a topic or a sub-task of a task. The computer-implemented graph is learned based upon content of search logs, and is used to output exploratory suggestions, where a user is exploring a topic or attempting to complete a multi-step task.

Abstract: In many computing scenarios, an individual may choose to interact with a service in a variety of roles, and may therefore create a set of accounts respectively representing the service. However, the use of multiple accounts by the same individual may introduce considerable administrative complications (e.g., failing to update all accounts with new information results in stale and/or conflicting account information), and may reduce the efficiency and/or scalability of the service. Presented herein are techniques for enabling individuals to interact with services through various roles. Such techniques involve evaluating the individual's role determinants to identify and automatically select the individual's current role; selecting a current role profile, as a subset of the details of the individual profile that are associated with the current role, and excluding details that are not associated with the current role; and performing the service according to the current role profile of the individual.

Abstract: Disclosed are techniques for extracting, identifying, and consuming imprecise temporal elements (“ITEs”). A user input may be received from a client device. A prediction may be generated of one or more time intervals to which the user input refers based upon an ITE model. The user input may be associated with the prediction, and provided to the client device.

Abstract: An example system for presenting search results includes a computer memory and a processor. The processor is to receive a set of search results in response to a query. The processor is to extract a feature and text from each of the search results. The processor is to also calculate an accessibility score for each of the search results based on the extracted feature and the text. The processor is to further rank the set of search results based on the accessibility score. The processor is to also further present the ranked search results based on an accessibility score of a user.

Abstract: The claimed subject matter includes a system and method for attribution of search activity in multi-user settings. The method includes training a classifier to distinguish between machines that are single-user and multi-user based on activity logs of an identified machine. The identified machine is determined to be multi-user based on the classifier. A number of users is estimated for the identified machine. Activity of the users is clustered based on the number of users estimated. A similarity function is learned for the number of users estimated. The method also includes assigning new activity to one of the users based on the clustering, and the similarity function.

Abstract: In many computing scenarios, an individual may choose to interact with a service in a variety of roles, and may therefore create a set of accounts respectively representing the service. However, the use of multiple accounts by the same individual may introduce considerable administrative complications (e.g., failing to update all accounts with new information results in stale and/or conflicting account information), and may reduce the efficiency and/or scalability of the service. Presented herein are techniques for enabling individuals to interact with services through various roles. Such techniques involve evaluating the individual's role determinants to identify and automatically select the individual's current role; selecting a current role profile, as a subset of the details of the individual profile that are associated with the current role, and excluding details that are not associated with the current role; and performing the service according to the current role profile of the individual.

Abstract: In many computing scenarios, an individual may interact with a device in a variety of roles, such as a student, an intern, and a gamer. While the individual may utilize the device in different ways for each role (e.g., using a particular set of files, applications, websites, and services), the device is not typically informed of the individual's role, and provides generalized device behavior irrespective of the individual's role. Presented herein are techniques for adapting device behavior based on the current role of the individual. Such techniques involve evaluating the individual's role determinants to identify and automatically select the individual's current role; selecting a current role profile, as a subset of the details of the individual profile that are associated with the current role, and excluding details that are not associated with the current role; and adjusting the device behavior according to the current role profile of the individual.

Abstract: One or more techniques and/or systems are provided for providing an answer scheme for an information request. For example a requester user may submit an information request seeking an informational answer (e.g., how far is the moon from the Earth; what are fun Cancun activities; is my drawing an accurate octagon; etc.). The information request may be evaluated to identify an information request property (e.g., an interesting property, a factual question property, an opinion property, an expertise level property, etc.). An answerer pool and/or an interaction type may be identified based upon the information request property (e.g., a chat group of scientists, a onetime text message answer from a paid expert, a vacation forum, a screen sharing session, etc.). An answer scheme, comprising the answerer pool and/or the interaction type, may be provided to the requester user for obtaining the informational answer.