Microsoft Technology Licensing, LLC

Meta Platforms, Inc.

Alexander J Kolmykov-Zotov

Steven P Dodge

Reed L Townsend

Rudolph Balaz

Manoj Kumar Biswas

Brigette Krantz

Steve Dodge

Arin J Goldberg

Kyril Feldman

Shenbagalakshmi Pichaiah

Bryan Douglas Scott

Emily K Rimas-Ribikauskas

Robert J Jarrett

Shiraz M Somji

Matt Lerner

Xin Wang

Sashi Raghupathy

Philip Ti-Fei Su

Ahmed Aly

Sam J George

Shrey Desai

Akshat Shrivastava

Alexander G Gounares

Leroy B Keely

Patrick Markus Baudisch

Yue Liu

Xiao Tu

Andrew L Silverman

Subha Bhattacharyay

David Leo Wright Hall

John P Bufe, Iii

Todd A Torset

Daniel Louis Klein

Jesse Daniel Eskes Rusak

Timothy H Kannapel

Jayant Sivarama Krishnamurthy

Brian Ewanchuk

Todd M Landstad

Koji Kato

Adam David Pauls

Pierce I-Jen Chuang

David Ernesto Heekin Burkett

Shawn A Van Ness

Jacob Daniel Andreas

Stephen Alan Fisher

Jason Andrew Wolfe

Vladimir V Smirnov

Stefan Wick

Denis Savenkov

Wayne Zeng

Kevin Welton

Richmond Lough

Chandramouli Kompella

Hongan Wang

Michael Russell

Pooja Sethi

Abhinav Arora

Arun Babu

Townsend Reed

In one embodiment, a method includes receiving training utterances associated with a domain, receiving ontology labels for the domain, wherein the ontology labels comprise one or more of an intent or a slot, generating an inventory for the domain, wherein the inventory comprises at least a respective index and respective span for each intent or slot, wherein the respective span comprises a respective descriptive label associated with the intent or slot, and wherein the respective descriptive label comprises a natural-language description of the intent or slot, generating frames for training utterances based on the training utterances and the inventory by a natural-language understanding (NLU) model, wherein each frame comprises a structural representation of the respective training utterance, wherein the structural representation is generated based on a comparison between the corresponding training utterance and the inventory, and updating the NLU model based on the frames.

Low-resource task-oriented semantic parsing via intrinsic modeling for assistant systems

In one embodiment, a method includes receiving a user input comprising input tokens from a client system, parsing the user input to determine ontology tokens and utterance tokens corresponding to the input tokens, decoding the ontology tokens and the utterance tokens to generate a span-based frame representation comprising intents, slots, and a span, wherein the ontology tokens are decoded into the intents and slots, and wherein the utterance tokens are decoded to determine the span comprising one or more tokens of the input tokens, wherein the span comprises a first index endpoint associated with a first token of the one or more tokens and a second index endpoint associated with a second token of the one or more tokens, and executing, responsive to the user input, one or more tasks based on the span-based frame representation.

Span pointer networks for non-autoregressive task-oriented semantic parsing for assistant systems

In one embodiment, a method includes receiving a user request to automatically debug a natural-language understanding (NLU) model, accessing a plurality of predicted semantic representations generated by the NLU model, wherein the plurality of predicted semantic representations are associated with a plurality of dialog sessions, respectively, wherein each dialog session is between a user and an assistant xbot associated with the NLU model, generating a plurality of expected semantic representations associated with the plurality of dialog sessions based on an auto-correction model, wherein the auto-correction model is learned from dialog training samples generated based on active learning, identifying incorrect semantic representations of the predicted semantic representations based on a comparison between the predicted semantic representations and the expected semantic representations, and automatically correcting the incorrect semantic representations by replacing them with respective expected semantic representations generated by the auto-correction model.

Continuous learning for natural-language understanding models for assistant systems

Methods of controlling the display and use of a UI element are disclosed. In an embodiment, the UI element may configured so that it initially maintains a topmost position but eventually allows other applications to assume the topmost position. In an embodiment, the display of the element may be adjusted in response to an input so that the UI element is not visible on the display. In an embodiment, the use of the UI element may allow for seamless dragging of the UI element even if the user inadvertently fails to make consistent contact with the touch-sensitive display while dragging the UI element.

Assisting user interface element use

A method, comprising recognizing a user utterance for processing. The method further comprises using a previously-trained code-generation machine to generate, from the user utterance, a data-flow program configured to produce a return value upon successful execution. The method further comprises beginning execution of the data-flow program. Responsive to reaching an error condition resulting from execution of the data-flow program, the method further comprises, prior to the data-flow program producing the return value, suspending execution of the data flow program. The method further comprises using the previously-trained code-generation machine to generate an error-handling data-flow program, wherein the error-handling data-flow program is configured to produce the return value; beginning execution of the error-handling data-flow program to produce the return value; and outputting the return value.

Error recovery for conversational systems

A method for rejecting an unintentional palm touch is disclosed. In at least some embodiments, a touch is detected by a touch-sensitive surface associated with a display. Characteristics of the touch may be used to generate a set of parameters related to the touch. In an embodiment, firmware is used to determine a reliability value for the touch. The reliability value and the location of the touch is provided to a software module. The software module uses the reliability value and an activity context to determine a confidence level of the touch. In an embodiment, the confidence level may include an evaluation of changes in the reliability value over time. If the confidence level for the touch is too low, it may be rejected.

Unintentional touch rejection

Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Shape recognition using partial shapes

Aspects of the invention provide virtual hover zones. When a user lowers a hovering stylus while remaining within a hover zone, cursor control is modified to be more easily controllable by the user. If the user pauses the stylus in mid-air before lowering the stylus, and if the stylus remains within the hover zone, then upon touchdown the cursor may be moved to the projection of the location where the stylus was paused. Any action that may be taken in response to the touch down may be sent to the projection location as well. Also provided are cursor control zones. A dampening zone may be used to provide dampened cursor movement feedback in response to movement input provided by a pointing device. Also, a dead zone may be used to prohibit cursor movement in response to movement input provided by the pointing device.

Targeting in a stylus-based user interface

Growing community of inventors

Sammamish, WA, United States of America

Alexander J Kolmykov-Zotov