International Business Machines Corporation

Xerox Corporation

Automotive Technologies International, Inc.

Other

Activision Publishing, Inc.

King.com Limited

Intelligent Technologies International, Inc.

Breed Corporation

Vittorio R Castelli

David S Breed

Lawrence David Bergman

Radu Florian

Chung-Sheng Li

Clifford A Pickover

Lloyd A Williams

Avirup Sil

Rick A Hamilton, Ii

Peter Anthony Franaszek

Taesun Moon

Daniel A Oblinger

Brian M O'Connell

Keith R Walker

Wendell C Johnson

Tessa Ann Lau

John Richard Smith

Anthony Stanley Pruszenski, Jr

Stephen T Chai

Joannes N M deJong

Richard M Dastin

Martin Franz

Joannes N deJong

Shikhar Kwatra

Yuan-Chi Chang

John Timothy Robinson

Barry M Wolf

Sarbajit Kumar Rakshit

Wilbur E DuVall

Philip Heidelberger

Sushain Pandit

Meng H Lean

Philip Shilung Yu

Wilbur E Duvall

James R Cassano

Michail Vlachos

Joannes N M De Jong

Matthew Leon Hill

John Joseph Turek

Bing Hua Zhao

Philip Shi-lung Yu

Daniel Clark Park

Gerald A Domoto

Elias Panides

John J Ritsko

Matthew Dondiego

Ryan Hamilton Breed

Osman Todd Polatkan

Peter Kenneth Malkin

Ashish Kundu

Jeffrey J Folkins

Komminist S Weldemariam

John David Wilson

Robert Anthony Street

Steven Robert Moore

Florian Pinel

David Nahamoo

Scott Alan Elrod

Robert G Farrell

Robert William Wisniewski

John F Knapp

Robert Michael Lofthus

Thomas Acquaviva

David L Hecht

William J Nowak

Richard G Stearns

Richard Edwin Harper

Alfio Massimiliano Gliozzo

Steven A Buhler

Gregory J Kovacs

Eric Alan Merz

John S Berkes

William Thomas Sanders

Paul N Krystek

Jan Bares

Thomas David Erickson

Prabhakar Nandavar Kudva

Henry R Till

Joy Roy

Charles Otto Schulz

Richard L Weisfield

Donald Leonard Smith

Dan Edward Poff

James M Casella

Luis A Lastras

Robert J Kleckner

Joy Aloysius Thomas

Gregory Joseph Kovacs

Brent Tzion Hailpern

Ming-Syan Chen

G A Connell

Salim Estephan Roukos

Gaetano Rossiello

Sameer Maskey

Steven Mark Harrison

Frank J McGrath

Wendy Anne Kellogg

Lawrence R Benedict

John J Ricciardelli

Sarthak Dash

Embodiments relate to an artificial intelligence (AI) computer platform to incorporate synthetic data and ground truth data, and to promote diversity and accuracy in generating the synthetic data. Synthetic questions are generated by a question generator in response to semantically related ground truth passage and answer data. Each generated question is presented to an answer generator together with the semantically related ground truth passage. Each synthetic question is evaluated with respect to its diversity from previous synthetic questions generated for the same ground truth passage and answer data. Each synthetic question is also evaluated with respect to the accuracy of the answer generated by the answer generator. A reward function that captures both accuracy and diversity of each synthetic question is leveraged to selectively modify the question generator, with the selective modification(s) directed at increasing textual diversity and maintaining accuracy of the generated synthetic questions.

Automatically generating diverse text

A method and system are provided for combining models. The method includes forming, by a computer having a processor and a memory, model pairs from a model ensemble that includes a plurality of models. The method further includes comparing the model pairs based on sets of output results produced by the model pairs to provide comparison results. The method also includes constructing, by the computer, a combination model from at least one of the model pairs based on the comparison results. The comparing step is performed using user-generated set-based feedback.

Search, question answering, and classifier construction

In an approach to synchronize notifications created in a VR environment to be presented in a physical environment at another time, notifications may be mapped across all relevant environments and associated with conditions that, when triggered, cause a notification to be presented to the user. Computer-implemented methods may include receiving natural language requests at a computing device in a first environment at a first time; parsing the natural language request into semantic components comprising an alert component and a content component; determining one or more conditions based on the alert component and the content component; mapping the semantic components to the plurality of environments; and executing a notification by the computing device, the notification representing the alert component and the content component in a second environment of the plurality of environments if the one or more conditions is satisfied at a second time that is later than the first time.

Synchronizing virtual reality notifications

A computer-implemented method according to one embodiment includes converting an input question into a vector form using trained word embeddings; constructing a type similarity matrix using a predetermined ontology; and determining a score for all possible types for the input question, based on the input question in vector form and the type similarity matrix.

Performing fine-grained question type classification

Embodiments relate to a system, program product, and method for use with an intelligent computer platform and cognitive processing and associated distribution. The embodiments support a mechanism for dynamically sharing critical and non-critical information responsive to a classification model, such that only relevant information or part of the information is shared. As the classification model is subject to modification, the dynamic sharing mechanism is dynamically updated to reflect such modification. Similarly, as an associated document or file is subject to modification, dynamic processing of the document or file takes place responsive to the classification model. The dynamic classification and document processing employ NLP and ML models to support the associated functionality.

Cognitive hierarchical content distribution

A processor may receive a text segment. The processor may analyze the text segment at a plurality of granularity levels wherein each of the plurality of granularity levels has a comparative selection value for identifying one or more objects of interest within the text segment. The processor may select an optimized granularity level with an optimum comparative selection value. The processor may identify the one or more objects of interest within the text segment. The processor may display the one or more objects of interest to a user.

Text classification using models with complementary granularity and accuracy

Described are techniques for video conversion for accessibility including a technique comprising determining, using data from at least one camera, that a user is distracted based on a direction of gaze of the user with respect to a display device presenting video content. The technique further comprises converting, by a machine learning model, the video content to audio content in response to determining the user is distracted, wherein the audio content comprises a description of the video content. The technique further comprises outputting, using at least one speaker, the audio content to the user while the user is distracted.

Video content conversion

Embodiments for intelligent media data filtering in an Internet of Things (IoT) computing environment by a processor. User preferences for the media data may be determined according to a plurality of identified contextual factors. At least a portion of the media data may be filtered according to one or more user classifications.

Filtering media data in an internet of things (IoT) computing environment

A personalized scheduling and networking method, system, and non-transitory computer readable medium include creating a user persona profile based on user information, extracting scheduling and networking information based on event information, matching a user with events during a conference based on the extracted scheduling and networking information and the user persona profile, and creating a schedule and a route for maximizing a number of the events and networking opportunities based on matches of the matching.

Personalized scheduling and networking system, method, and recording medium

Embodiments for managing a voice response system by one or more processors are described. At least one communication from an individual is received. A reference to a previous response executed by a voice response system is identified within the at least one received communication. A response to the at least one received communication is determined based on the previous response executed by the voice response system.

Methods and systems for managing voice response systems based on references to previous responses

A method and system is provided for item inquiry and information presentation via standard communication paths. More particularly, the method and system detects an item associated with an avatar of a virtual universe (VU) user in a VU and determine information associated with the item. Additionally, the method and system are operable to display the information in the VU in a high-resolution component of the VU.

System and method for item inquiry and information presentation via standard communication paths

A roadway condition predictive model that can recommend ameliorative roadway action(s) is disclosed. A roadway controller computer acquires sensor and location information, which describe physical driving surface conditions on the roadway, from a plurality of vehicles that travel on the roadway. The roadway controller computer also acquires environmental and traffic conditions for the roadway. The roadway controller computer creates a predictive model that describes a deterioration rate and future physical condition of the roadway, based on the acquired sensor, location information, environmental and traffic conditions for the roadway. The roadway controller computer then implements an action to ameliorate deterioration of the roadway that is predicted by the predictive model.

Roadway condition predictive models

A computer-implemented computer documentation validation method, the method comprising: manipulating a user interface of an operating system by taking control of a user input device to execute a command of a computer software documentation on behalf of the user; and outputting an error code when a failure is a result of the executed command.

Validating computer documentation via error detection in a natural language of the computer documentation

A query expansion method, system, and computer program product, include establishing a context of a query to execute the query within a search index by labeling phrases of interest of the query, expanding of the phrases of interest based on a language model and a topic model, and identifying and incorporating an available historical query into the context according to a historical phrase of interest and an expansion of one or more historical phrases of interest, and retrieving and displaying one or more search results based on the query and the context of the query as a first visual mark indicating a linkage between one or more terms of the query and the one or more search results and a second visual mark indicating an alignment between the available historical query and a match to the terms of the query and the search result.

Query expansion

An unmanned aerial vehicle for determining geolocation foraging zones for animals, the unmanned aerial vehicle comprising a processor-based monitoring device to monitor a plurality of geolocations, an identification device to identify an animal and to track a position of the animal in relation to the plurality of geolocations, a risk analysis device to evaluate a level of risk associated with each of the plurality of geolocations, and a mapping device coupled to the monitoring device to select a geolocation foraging zone when the level of risk associated with the geolocation foraging zone is below a predetermined threshold value.

Unmanned aerial vehicle for determining geolocation foraging zones

Growing community of inventors

Yorktown Heights, NY, United States of America

Vittorio R Castelli