Abstract: In one embodiment, a method includes receiving a user query inputted on a head-mounted device from the head-mounted device, wherein the user query corresponds to multiple dialog-intents, executing multiple tasks corresponding to the multiple dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the multiple tasks, wherein the stitching model combines the two or more of the execution results based on natural language processing, and wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and sending instructions to the head-mounted device for presenting the multi-perspective response on the head-mounted device.

Abstract: In one embodiment, a method includes receiving a user query inputted on a head-mounted device from the head-mounted device, wherein the user query corresponds to multiple dialog-intents, executing multiple tasks corresponding to the multiple dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the multiple tasks, wherein the stitching model combines the two or more of the execution results based on natural language processing, and wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and sending instructions to the head-mounted device for presenting the multi-perspective response on the head-mounted device.

Abstract: In one embodiment, a method includes receiving a user query associated with dialog-intents at a client system, executing tasks corresponding to the dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the tasks, wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and presenting the multi-perspective response at the client system.

Abstract: In one embodiment, a method includes receiving a user query inputted on a head-mounted device from the head-mounted device, wherein the user query corresponds to multiple dialog-intents, executing multiple tasks corresponding to the multiple dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the multiple tasks, wherein the stitching model combines the two or more of the execution results based on natural language processing, and wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and sending instructions to the head-mounted device for presenting the multi-perspective response on the head-mounted device.

Abstract: Methods and apparatus for interfaces to manage virtual network interface objects. A system may include resource instances and a network interface virtualization coordinator. Responsive to a record creation request, the coordinator creates an interface records that may include an IP address, subnet information and security properties. The coordinator may, in response to a request to attach the record to a resource instance, enable traffic directed to the IP address to flow to the resource instance. In response to a subsequent detach request, the traffic to the IP address may be disabled at the resource instance. The same interface record may be attached to another resource instance in response to another attach request, enabling traffic directed to the IP address to flow to the second resource instance.

Abstract: In one embodiment, a method includes receiving a user query from a client system associated with a first user, determining a plurality of dialog-intents, each being associated with a particular agent of a plurality of agents, executing a plurality of tasks corresponding to the user query via the plurality of agents corresponding to the plurality of dialog-intents, receiving a plurality of execution results corresponding to the plurality of tasks from the plurality of agents, respectively, selecting two or more of the plurality of execution results for combination, generating a multi-perspective response based on the selected execution results by a stitching model, wherein the multi-perspective response comprises a natural-language response combining the selected execution results, and sending instructions for presenting the multi-perspective response to the first user to the client system in response to the user query.

Abstract: In one embodiment, a method includes receiving a user query associated with dialog-intents at a client system, executing tasks corresponding to the dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the tasks, wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and presenting the multi-perspective response at the client system.

Abstract: In one embodiment, a method includes receiving a user query from a client system associated with a first user, determining a plurality of dialog-intents, each being associated with a particular agent of a plurality of agents, executing a plurality of tasks corresponding to the user query via the plurality of agents corresponding to the plurality of dialog-intents, receiving a plurality of execution results corresponding to the plurality of tasks from the plurality of agents, respectively, selecting two or more of the plurality of execution results for combination, generating a multi-perspective response based on the selected execution results by a stitching model, wherein the multi-perspective response comprises a natural-language response combining the selected execution results, and sending instructions for presenting the multi-perspective response to the first user to the client system in response to the user query.

Abstract: A set of search results associated with a query is received, the set of search results including for each of search result in at least a subset of the set an indication of an evidence based at least in part on which the search result was included in the set of search results. A search result display interface is generated in which at least a displayed subset of search results are displayed, the search result display interface include for each of at least a subset of the displayed search results an indication of the corresponding evidence based on which that search result was included in the set of search results.

Abstract: A computing device can generate a collection of phrases using both authoritative data and behavioral data, for example, using previously submitted search queries. The collection of phrases can be used, in part, to determine the best segmentation of search queries. Each segmentation of a search query splits the terms in search query using different permutations or n-grams to identify one or more phrases. Each segmentation is scored based on various criteria. The segmentation having the highest score is included in training data for training a predictive model that predicts segmentations for new search queries. The predicted segmentation can be used to annotate that query to identify the one or more phrases that were created by the segmentation of the query. The annotated query can be processed, for example, by a search engine, to obtain resources that are responsive to the one or more phrases that were identified by the segmentation.

Abstract: A user statement associated with a query is received. The user statement is parsed to determine a set of interpretations matching the user statement. Based at least in part on the set of interpretations the query is determined to be a candidate for iterative improvement. The query is iteratively improved at least in part by prompting a user associated with the user statement to provide a further input.

Abstract: A set of search results associated with a query is received, the set of search results including for each of search result in at least a subset of the set an indication of an evidence based at least in part on which the search result was included in the set of search results. A search result display interface is generated in which at least a displayed subset of search results are displayed, the search result display interface include for each of at least a subset of the displayed search results an indication of the corresponding evidence based on which that search result was included in the set of search results.

Abstract: A user statement associated with a natural query is received. A syntactic parse of the user statement is performed to generate a parsed user statement. The parsed user statement is matched against a set of one or more interpretations determined to have meaning in a context of a knowledge base with which the user statement is associated. A user intent is determined based at least in part on said one or more interpretations. A determined query is performed based on said user intent.

Abstract: Disclosed herein are embodiments of a compound capable of treating HIV. In particular disclosed embodiments, the compound is capable of inhibiting Nef, such as by acting as antagonists of HIV Nef function. Also disclosed are embodiments of a method of making the compound, embodiments of a method of using the compound, and embodiments of a method of identifying HIV Nef antagonists. The disclosed compound may be used alone or in combination with other pharmacologically active agents in order to promote reducing drug resistance and/or cumulative toxicity.

Abstract: A request is received to change an association of a network interface record from a first resource instance to a second resource instance. The network interface record may include an IP address associated with the first resource instance. In response to the request, the first resource instance is prevented from receiving data packets addressed to the IP address of the network interface record through a first network interface object attached to the first resource instance. The network interface record is associated with the second resource instance so that the second resource instance is enabled to receive data packets addressed to the IP address of the network interface record through a second network interface object attached to the second resource instance.

Abstract: Disclosed herein are embodiments of a compound capable of treating HIV. In particular disclosed embodiments, the compound is capable of inhibiting Nef, such as by acting as antagonists of HIV Nef function. Also disclosed are embodiments of a method of making the compound, embodiments of a method of using the compound, and embodiments of a method of identifying HIV Nef antagonists. The disclosed compound may be used alone or in combination with other pharmacologically active agents in order to promote reducing drug resistance and/or cumulative toxicity.

Abstract: The claimed system is a multicast programming model for implementation on top of a service oriented framework, specifically a service oriented messaging system. It provides application-layer multicast capability without requiring an IP multicast infrastructure. The claimed system enables service oriented applications to implement multicasting communications easily and efficiently.

Abstract: The claimed system is a service support framework for a multicast programming system implemented on top of a service oriented framework, specifically a service oriented messaging system.

Abstract: The claimed method and system is an API set to support a multicast programming model for implementation on top of a service oriented framework, specifically a service oriented messaging system.