Microsoft Technology Licensing, LLC

Other

Paul Nathan Bennett

Ryen William White

Susan Theresa Dumais

Kevyn Breca Collins-Thompson

Adam Fourney

Chenyan Xiong

Saurabh Kumar Tiwary

Xia Song

Eric J Horvitz

Paramvir Bahl

David Maxwell Chickering

Tim Paek

Milad Shokouhi

Corbin Louis Rosset

Christopher Brian Quirk

Wei Dong Wang

Ahmed Hassan Awadallah

Emre Mehmet Kiciman

Nicholas Eric Craswell

Russell Allen Herring, Jr

Sebastian De La Chica

Daniel Fernando Campos

Corby Louis Rosset

Saghar Hosseinisianaki

Xin Rong

David Graus

David Alexander Sontag

Jianfeng Gao

Christopher A Meek

Timothy S Paek

Chen Zhao

Krysta Marie Svore

Michael Gamon

Jaime Brooks Teevan

Karthik Raman

Asela J Gunawardana

Peter Bailey

Anton Mityagin

Daniel John Liebling

Nikhil Dandekar

Nikrouz Ghotbi

Sandeep S Sahasrabudhe

Richard Lloyd Hughes

Filip Andrzej Radlinski

Aparna Lakshmiratan

Nirupama Chandrasekaran

Prabhdeep Singh

Anne Loomis Thompson

Adam D Troy

Longqi Yang

Richard A Caruana

Nicholas Craswell

Emine Yilmaz

Ragavenderan Venkatesan

Hongfei Zhang

Siranush Sarkizova

Marc Sloan

Lidan Wang

Huizhong Duan

Qian Zhao

David A Sontag

Jagadeesh Jagarlamudi

Kristen Patricia Parton

Vitor R Carvalho

Nam H Nguyen

Ramakrishna B Bairi

Benjamin Austin Carterette

Tobias Benjamin Schnabel

Richard L Hughes

Eric Joel Horvitz

A computer-implemented technique is described herein for assisting a user in advancing a task objective. The technique uses a suggestion-generating system (SGS) to provide one or more suggestions to a user in response to at least a last-submitted query provided by the user. The SGS may correspond to a classification-type or generative-type neural network. The SGS uses a machine-trained model that is trained using a multi-task training framework based on plural groups of training examples, which, in turn, are produced using different respective example-generating methods. One such example-generating method constructs a training example from queries in a search session. It operates by identifying the task-related intent the queries, and then identifying at least one sequence of queries in the search session that exhibits a coherent task-related intent. A training example is constructed based on queries in such a sequence.

Using a multi-task-trained neural network to guide interaction with a query-processing system via useful suggestions

This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.

Inter-document attention mechanism

The present concepts relate to a differentiable user-item co-clustering ('DUICC') model for recommendation and co-clustering. Users' interaction with items (e.g., content) may be centered around information co-clusters&#x2014;groups of items and users that exhibit common consumption behavior. The DUICC model may learn fine-grained co-cluster structures of items and users based on their interaction data. The DUICC model can then leverage the learned latent co-cluster structures to calculate preference stores of the items for a user. The top scoring items may be presented to the user as recommendations.

Differentiable user-item co-clustering

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.

System for interpreting and managing imprecise temporal expressions

Generally discussed herein are devices, systems, and methods for identifying a purpose of a communication. A method can include receiving a communication including communication content and communication context, the communication content a first portion of the communication and the communication context a second, different portion of the communication. The method can include identifying, by a machine learning (ML) model, based on the communication content and the communication context, one or more purposes associated with the communication, the one or more purposes indicating respective actions to be performed by a user that generated or received the communication. The method can include providing data indicating the purpose of the first portion of the content.

Purpose detection in communications using machine learning

Generally discussed herein are devices, systems, and methods for resource retrieval. A method may include determining that a calendar event is scheduled to occur in a specified period of time, responsive to the determination, extracting content of a calendar event on a calendar of the messaging interface, generating a list of resources accessible by the user and related to the extracted content of the calendar event, ranking the resources by a comparison of the extracted content of the calendar event and the content of resources of the list of resources, and causing respective summaries of a specified number of the respective resources with higher respective ranks to be output on the display.

Calendar-aware resource retrieval

A computer-implemented technique receives an input expression that a user submits with an intent to accomplish some objective. The technique then uses a machine-trained intent encoder component to map the input expression into an input expression intent vector (IEIV). The IEIV corresponds to a distributed representation of the intent associated with the input expression, within a vector intent vector space. The technique then leverages the intent vector to facilitate some downstream application task, such as the retrieval of information. Some application tasks also use a neighbor search component to find expressions that express an intent similar to that of the input expression. A training system trains the intent encoder component based on the nexus between queries and user clicks, as recorded in a search engine's search log.

Intent encoder trained using search logs

A digital task document can include instructions for performing a task, and a task state data structure can indicate a state of completion of the task. A first update of the data structure can be performed in response to visual user input received from a user profile via a first computer application/device. A second update of the data structure can be performed in response to natural language input received from the user profile via the second computer application/device. A first set of task guidance can be provided to the user profile via the first application/device in a visual format by displaying the task document on a computer display. A second set of task guidance can be provided to the user profile via the second application/device in a natural language format. The first and second sets of task guidance can be provided using the task document and the data structure.

Computerized task guidance across devices and applications

Various technologies related to generating and applying content retrieval rules are described herein. A content retrieval rule maps a combination of a query and a context to one of a query reformulation or content. The content retrieval rule is learned from search logs of a search engine, and is applied when the query having the context is received at the search engine.

Learning and using contextual content retrieval rules for query disambiguation

A system that analyses content of electronic communications may automatically extract requests or commitments from the electronic communications. In one example process, a processing component may analyze the content to determine one or more meanings of the content; query content of one or more data sources that is related to the electronic communications; and based, at least in part, on (i) the one or more meanings of the content and (ii) the content of the one or more data sources, automatically identify and extract a request or commitment from the content. Multiple actions may follow from initial recognition and extraction, including confirmation and refinement of the description of the request or commitment, and actions that assist one or more of the senders, recipients, or others to track and address the request or commitment, including the creation of additional messages, reminders, appointments, or to-do lists.

Automatic extraction of commitments and requests from communications and content

Growing community of inventors

Redmond, WA, United States of America

Paul Nathan Bennett