Microsoft Technology Licensing, LLC

Meta Platforms, Inc.

Facebook, Inc.

Carlos Garcia Jurado Suarez

Aparna Lakshmiratan

Denis X Charles

David G Grangier

David Maxwell Chickering

Patrice Y Simard

Xiaohu Liu

Benoit F Dumoulin

Baiyang Liu

Geoffrey G Zweig

David Max Chickering

Leon Bottou

Christopher A Meek

Darko Kirovski

Jitendra Dattatraya Padhye

Jacob Rubin Lorch

Jason D Williams

Saleema Amin Amershi

Richard Lloyd Hughes

Siddhartha Sen

Curtis N Von Veh

Andrey Kolobov

Nobal Bikram Niraula

Pradeep Dasigi

Steven Mark Drucker

Bongshin Lee

Jason Paul Williams

Ian M Bavey

Jing Fan

Niall L McDonnell

Patrice Yvon Rene Simard

Jack Joseph J Greenfield

In one embodiment, a method includes receiving a user request from a first user at a client system, wherein the user request is associated with a semantic-intent, identifying dialog-intents associated with the user request by the client system based on the semantic-intent and context information associated with the user request, wherein each dialog-intent is a sub-intent of the semantic-intent; determining agents for executing tasks associated with the dialog-intents by the client system, and presenting information returned from the agents responsive to executing the tasks at the client system.

Intent identification for agent matching by assistant systems

In one embodiment, a method includes receiving a user request from a client system associated with a first user, wherein the user request is associated with a semantic-intent, identifying one or more dialog-intents associated with the user request based on the semantic-intent and context information associated with the user request, wherein each dialog-intent is a sub-intent of the semantic-intent, determining one or more agents for executing one or more tasks associated with the one or more dialog-intents, and sending instructions for presenting information returned from the one or more agents responsive to executing the one or more tasks to the client system.

Techniques for employing a decentralized sleep management service are described herein. In some instances, each computing device of a group of computing devices periodically shares information about itself with each other computing device of the group. With this information, each computing device within the group that is awake and capable of managing other devices selects a subset of devices to probe. The devices then probe this subset to determine whether the probed devices are asleep. In response to identifying a sleeping device, the probing device takes over management of the sleeping device. Managing the sleeping device involves informing other devices of the group that the sleeping device is being managed, in addition to monitoring requests for services on the sleeping device. In response to receiving a valid request for a service hosted by the sleeping device, the managing device awakens the sleeping device and ceases managing the now-woken device.

Decentralized sleep management

Domain-specific language understanding models that may be built, tested and improved quickly and efficiently are provided. Methods, systems and devices are provided that enable a developer to build user intent detection models, language entity extraction models, and language entity resolution models quickly and without specialized machine learning knowledge. These models may be built and implemented via single model systems that enable the models to be built in isolation or in an end-to-end pipeline system that enables the models to be built and improved in a simultaneous manner.

Generation of language understanding systems and methods

In one embodiment, a method includes receiving a user request associated with one or more domains from a client system associated with a first user, parsing the user request to identify one or more semantic-intents are associated with the one or more domains and one or more slots, identifying, based on a ranker model, one or more dialog-intents associated with the user request based on the one or more semantic-intents and slots and context information associated with the user request, wherein each dialog-intent is a sub-intent of one or more of the semantic-intents, determining one or more agents for executing one or more tasks associated with the one or more dialog-intents respectively, and sending instructions for presenting a communication content information returned from the one or more agents responsive to executing the one or more tasks responsive to the user input to the client system.

Methods, computer systems, computer-storage media, and graphical user interfaces are provided for visualizing a performance of a machine-learned model. An interactive graphical user interface includes an item representation display area that displays a plurality of item representations corresponding to a plurality of items processed by the machine-learned model. The plurality of item representations are arranged according to scores assigned to the plurality of items by the machine-learned model. Further, each of the plurality of item representations is visually configured to represent a label assigned to a corresponding item.

Interactive visualization of machine-learning performance

A collection of data that is extremely large can be difficult to search and/or analyze. Relevance may be dramatically improved by automatically classifying queries and web pages in useful categories, and using these classification scores as relevance features. A thorough approach may require building a large number of classifiers, corresponding to the various types of information, activities, and products. Creation of classifiers and schematizers is provided on large data sets. Exercising the classifiers and schematizers on hundreds of millions of items may expose value that is inherent to the data by adding usable meta-data. Some aspects include active labeling exploration, automatic regularization and cold start, scaling with the number of items and the number of classifiers, active featuring, and segmentation and schematization.

Feature completion in computer-human interactive learning

Conversational interactions between humans and computer systems can be provided by a computer system that classifies an input by conversation type, and provides human authored responses for conversation types. The input classification can be performed using trained binary classifiers. Training can be performed by labeling inputs as either positive or negative examples of a conversation type. Conversational responses can be authored by the same individuals that label the inputs used in training the classifiers. In some cases, the process of training classifiers can result in a suggestion of a new conversation type, for which human authors can label inputs for a new classifier and write content for responses for that new conversation type.

Generating computer responses to social conversational inputs

Interactive segment extraction in computer-human interactive learning

A system is described for allowing a user, operating a trusted device, to remotely log into a server via a potentially untrustworthy client. A first secure connection is established between the client and the server. A second secure connection is established between the device and the server through the client. The user then remotely logs into the server over the second secure connection using the device. The second secure connection is tunneled within the first secure connection, preventing the untrustworthy client from discovering personal information associated with the user. According to one feature, prior to forming the second secure connection, the user establishes a pairing relationship with the client by reading an address of the client using a reading mechanism. According to another feature, the device can receive marketing information in the course of a transaction.

Device-pairing by reading an address provided in device-readable form

A system is described for allowing a user, operating a trusted device, to remotely log into a server via a potentially untrustworthy client. The system operates by establishing a first secure connection between the client and the server. The system then establishes a second secure connection between the device and the server through the client. The user then remotely logs into the server over the second secure connection using the device. The second secure connection is tunneled within the first secure connection, preventing the untrustworthy client from discovering personal information associated with the user. According to one feature, prior to forming the second secure connection, the user can establish a pairing relationship with the client by reading an address of the client using any kind of reading mechanism. According to another feature, the device can receive marketing information in the course of a transaction.

The present invention provides systems and methods that synchronize modifications between electronic data and one or more associated data representations. Synchronization comprises translating modification made to the data or a representation to the representations or the data and other representations. A mapping engine is employed to facilitate modification translation, wherein the mapping engine utilizes data-representation relationships, which declaratively described the relationship between data and respective representations. Such relationships can be stored in markup language (e.g., xml) or as a memory string, for example. Modifications can be translated via a continuous technique, wherein translation occurs upon transaction commitment or via an explicit technique, wherein translation occurs upon an explicit request. The systems and methods further employ an adapter that facilitates communication between the mapping engine and the representation and a handler store that provides various handlers that facilitates communication between the mapping engine and data.

Systems and methods that synchronize data with representations of the data

Growing community of inventors

Redmond, WA, United States of America

Carlos Garcia Jurado Suarez