Patents by Inventor Aparna Lakshmiratan
Aparna Lakshmiratan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11023677Abstract: 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.Type: GrantFiled: July 13, 2016Date of Patent: June 1, 2021Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Patrice Y. Simard, David Max Chickering, David G. Grangier, Aparna Lakshmiratan, Saleema A. Amershi
-
Patent number: 10909969Abstract: 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.Type: GrantFiled: September 25, 2019Date of Patent: February 2, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Jason Douglas Williams, Nobal Bikram Niraula, Pradeep Dasigi, Aparna Lakshmiratan, Geoffrey G. Zweig, Andrey Kolobov, Carlos Garcia Jurado Suarez, David Maxwell Chickering
-
Publication number: 20200020317Abstract: 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.Type: ApplicationFiled: September 25, 2019Publication date: January 16, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Jason Douglas WILLIAMS, Nobal Bikram NIRAULA, Pradeep DASIGI, Aparna LAKSHMIRATAN, Geoffrey G. ZWEIG, Andrey KOLOBOV, Carlos GARCIA JURADO SUAREZ, David Maxwell CHICKERING
-
Patent number: 10460720Abstract: 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.Type: GrantFiled: April 3, 2015Date of Patent: October 29, 2019Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.Inventors: Jason Douglas Williams, Nobal Bikram Niraula, Pradeep Dasigi, Aparna Lakshmiratan, Geoffrey G. Zweig, Andrey Kolobov, Carlos Garcia Jurado Suarez, David Maxwell Chickering
-
Patent number: 9886669Abstract: 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.Type: GrantFiled: February 26, 2014Date of Patent: February 6, 2018Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Saleema A. Amershi, Steven M. Drucker, Bongshin Lee, Patrice Yvon Rene Simard, Aparna Lakshmiratan, Carlos Garcia Jurado Suarez, Denis X. Charles, David G. Grangier, David Maxwell Chickering
-
Patent number: 9582490Abstract: 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.Type: GrantFiled: November 8, 2013Date of Patent: February 28, 2017Assignee: Microsoft Technolog Licensing, LLCInventors: Patrice Y. Simard, David Max Chickering, Aparna Lakshmiratan, Denis X. Charles, Leon Bottou
-
Publication number: 20170039486Abstract: 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.Type: ApplicationFiled: July 13, 2016Publication date: February 9, 2017Inventors: Patrice Y. SIMARD, David Max CHICKERING, David G. GRANGIER, Aparna LAKSHMIRATAN, Saleema A. AMERSHI
-
Patent number: 9547471Abstract: 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.Type: GrantFiled: July 3, 2014Date of Patent: January 17, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Jason Williams, Geoffrey Zweig, Aparna Lakshmiratan, Carlos Garcia Jurado Suarez
-
Patent number: 9489373Abstract: 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.Type: GrantFiled: November 8, 2013Date of Patent: November 8, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Patrice Y. Simard, David Max Chickering, David G. Grangier, Denis X. Charles, Leon Bottou, Saleema A. Amershi, Aparna Lakshmiratan, Carlos Garcia Jurado Suarez
-
Patent number: 9430460Abstract: 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.Type: GrantFiled: November 8, 2013Date of Patent: August 30, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Patrice Y. Simard, David Max Chickering, David G. Grangier, Aparna Lakshmiratan, Saleema A. Amershi
-
Publication number: 20160196820Abstract: 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.Type: ApplicationFiled: April 3, 2015Publication date: July 7, 2016Applicant: Microsoft Technology Licensing, LLC.Inventors: Jason Douglas Williams, Nobal Bikram Niraula, Pradeep Dasigi, Aparna Lakshmiratan, Geoffrey G. Zweig, Andrey Kolobov, Carlos Garcia Jurado Suarez, David Maxwell Chickering
-
Patent number: 9283476Abstract: Systems and methods allow an on-line game to extract information relevant to a specific need of a game platform or service platform. The specific need relates to management and use of digital content, and is addressed by designing and playing an on-line collaborative game. The rules of the game intend to solve a specific task dictated by the specific need. Players' responses to the game generate a wealth of information related to a specific task objective, such as ranking, sorting, and evaluating a set of digital content items. To compel participation in a game, players can be rewarded with monetary value rewards. As a game illustration, an image selection game (ISG) that exploits human contextual inference is described in detail. The information extracted from ISG is a list of key-image associations, relevant for the task of image sorting and ranking.Type: GrantFiled: August 22, 2007Date of Patent: March 15, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Anton Mityagin, Aparna Lakshmiratan, Asela J. Gunawardana, Christopher A. Meek, David M. Chickering, Paul N. Bennett, Timothy S. Paek
-
Publication number: 20160005395Abstract: 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.Type: ApplicationFiled: July 3, 2014Publication date: January 7, 2016Inventors: Jason Williams, Geoffrey Zweig, Aparna Lakshmiratan, Carlos Garcia Jurado Suarez
-
Publication number: 20150242761Abstract: 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.Type: ApplicationFiled: February 26, 2014Publication date: August 27, 2015Applicant: MICROSOFT CORPORATIONInventors: SALEEMA A. AMERSHI, STEVEN M. DRUCKER, BONGSHIN LEE, PATRICE YVON RENE SIMARD, APARNA LAKSHMIRATAN, CARLOS GARCIA JURADO SUAREZ, DENIS X. CHARLES, DAVID G. GRANGIER, DAVID MAXWELL CHICKERING
-
Publication number: 20150019463Abstract: 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.Type: ApplicationFiled: November 8, 2013Publication date: January 15, 2015Applicant: Microsoft CorporationInventors: PATRICE Y. SIMARD, DAVID MAX CHICKERING, DAVID G. GRANGIER, APARNA LAKSHMIRATAN, SALEEMA A. AMERSHI
-
Publication number: 20150019460Abstract: 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.Type: ApplicationFiled: November 8, 2013Publication date: January 15, 2015Applicant: Microsoft CorporationInventors: PATRICE Y. SIMARD, DAVID MAX CHICKERING, APARNA LAKSHMIRATAN, DENIS X. CHARLES, LEON BOTTOU
-
Publication number: 20150019461Abstract: 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.Type: ApplicationFiled: November 8, 2013Publication date: January 15, 2015Applicant: Microsoft CorporationInventors: PATRICE Y. SIMARD, DAVID MAX CHICKERING, DAVID G. GRANGIER, DENIS X. CHARLES, LEON BOTTOU, SALEEMA A. AMERSHI, APARNA LAKSHMIRATAN, CARLOS GARCIA JURADO SUAREZ
-
Patent number: 8799312Abstract: Systems, methods, and computer storage media having computer-executable instructions embodied thereon for rewriting queries and labeling word pairs. Queries are received and alternate words are identified for word pairs (i.e., query words and alternate words). Word pair links are presented to users and indicators are received based on actions taken by the users. Labels are assigned to the word pairs based on the indicators and communicated to a classifier.Type: GrantFiled: December 23, 2010Date of Patent: August 5, 2014Assignee: Microsoft CorporationInventors: Seyed Ali Ahmadi, Alnur Ali, Aparna Lakshmiratan, Deepak Agarwal, Sameer Yusufali Merchant, Michael Revow, Ahmad Abdulkader
-
Publication number: 20120166473Abstract: Systems, methods, and computer storage media having computer-executable instructions embodied thereon for rewriting queries and labeling word pairs. Queries are received and alternate words are identified for word pairs (i.e., query words and alternate words). Word pair links are presented to users and indicators are received based on actions taken by the users. Labels are assigned to the word pairs based on the indicators and communicated to a classifier.Type: ApplicationFiled: December 23, 2010Publication date: June 28, 2012Applicant: MICROSOFT CORPORATIONInventors: SEYED ALI AHMADI, ALNUR ALI, APARNA LAKSHMIRATAN, DEEPAK AGARWAL, SAMEER YUSUFALI MERCHANT, MICHAEL REVOW, AHMAD ABDULKADER
-
Publication number: 20100257019Abstract: Interactively associating user-defined descriptions with objects. At least two users create descriptions based on provided objects. The users analyze the descriptions to determine whether the users were provided with the same or different objects. If all the users are correct in their determinations, associations between the created descriptions and the corresponding objects are adjusted. In some embodiments, the users interact via a two-player game where the input is obfuscated and the output is optionally obfuscated. For example, the users each provide a search query responsive to receipt of a search intention. If a single search intention was provided and all the users make the correct determination, the search queries are associated with the search intention.Type: ApplicationFiled: April 2, 2009Publication date: October 7, 2010Applicant: Microsoft CorporationInventors: David Maxwell Chickering, Edith Lok Man Law, Anton Mityagin, Gonzalo Alberto Ramos, Aparna Lakshmiratan