Patents by Inventor Alexander Kolmykov-Zotov
Alexander Kolmykov-Zotov 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: 11861315Abstract: 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 repreType: GrantFiled: June 18, 2021Date of Patent: January 2, 2024Assignee: Meta Platforms, Inc.Inventors: Pooja Sethi, Denis Savenkov, Yue Liu, Alexander Kolmykov-Zotov, Ahmed Aly
-
Publication number: 20230419952Abstract: In one embodiment, a method includes receiving a request to train a natural-language understanding (NLU) model for a new domain, accessing a context-free grammar associated with the new domain, wherein the context-free grammar defines production rules with respect to ontology tokens associated with the new domain and utterance tokens for generating natural-language strings in the new domain, generating utterance-frame pairs based on traversing a hierarchical grammar tree associated with the context-free grammar based on the production rules, wherein each utterance-frame pair comprises an utterance and a corresponding frame, wherein each frame comprises ontology tokens associated with the new domain and utterance tokens corresponding to one or more of the ontology tokens of the frame, and training the NLU model based on the utterance-frame pairs.Type: ApplicationFiled: May 18, 2022Publication date: December 28, 2023Inventors: Shrey Desai, Theodore Frank Levin, Brian Moran, Daniel Difranco, Alexander Kolmykov-Zotov
-
Publication number: 20230245654Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.Type: ApplicationFiled: January 20, 2023Publication date: August 3, 2023Inventors: Akshat Shrivastava, Shrey Desai, Anchit Gupta, Ali Elkahky, Aleksandr Livshits, Alexander Kolmykov-Zotov, Ahmed Aly, Jinsong Yu, Manali Anand Naik, Shuhui Yang, Baiyang Liu, Surya Teja Appini, Tarun Vir Singh, Hang Su, Jiedan Zhu, Fuchun Peng, Shoubhik Bhattacharya, Kshitiz Malik, Shreyan Bakshi, Akash Bharadwaj, Harish Srinivas, Xiao Yang, Zhuangqun Huang, Gil Keren, Duc Hoang Le, Ahmed Kamal Atwa Mohamed, Zhe Liu, Pranab Mohanty
-
Publication number: 20230135179Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.Type: ApplicationFiled: October 6, 2022Publication date: May 4, 2023Inventors: Sebastian Jonathan Mielke, Arthur David Szlam, Emily Dinan, Y-Lan Boureau, Mokhtar Mohamed Khorshid, Jeremy Dohmann, Brian Moran, Lintao Cui, Jonathan Richard Goetz, Ahmed Kamal Atwa Mohamed, Paul Anthony Crook, Andrea Madotto, Shrey Desai, Alexander Kolmykov-Zotov, Jason Pazis, Zhaojun Yang, Haichuan Yang, Yangyang Shi, Biqiao Zhang, Ivaylo Enchev, Xin Lei, Ming Sun
-
Publication number: 20220415320Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.Type: ApplicationFiled: May 16, 2022Publication date: December 29, 2022Inventors: Pujie Zheng, Lin Sun, Ram Kumar Hariharan, Haidong Wang, Joshua Saylor McMullen, Mengxi Li, Long You Cai, Keith Diedrick, Crystal Annette Nakatsu Sung, Xi Chen, Stanislav Peshterliev, Debojeet Chatterjee, Sonal Gupta, Vikas Seshagiri Rao Bhardwaj, Yashar Mehdad, Anuj Kumar, Ashish Garg, Justin Denney, Hakan Inan, Iaroslav Markov, Surya Teja Appini, Bing Liu, Shusen Liu, Zhiqi Wang, Alexander Kolmykov-Zotov
-
Publication number: 20220374605Abstract: 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 repreType: ApplicationFiled: June 18, 2021Publication date: November 24, 2022Inventors: Pooja Sethi, Denis Savenkov, Yue Liu, Alexander Kolmykov-Zotov, Ahmed Aly
-
Patent number: 9613264Abstract: 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.Type: GrantFiled: December 10, 2015Date of Patent: April 4, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Alexander Kolmykov-Zotov, Sashi Raghupathy, Xin Wang
-
Publication number: 20160098593Abstract: 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.Type: ApplicationFiled: December 10, 2015Publication date: April 7, 2016Applicant: Microsoft Technology Licensing, LLCInventors: Alexander Kolmykov-Zotov, Sashi Raghupathy, Xin Wang
-
Patent number: 9218525Abstract: 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.Type: GrantFiled: December 18, 2013Date of Patent: December 22, 2015Assignee: Microsoft Technology Licensing, LLCInventors: Alexander Kolmykov-Zotov, Sashi Raghupathy, Xin Wang
-
Publication number: 20140104308Abstract: 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.Type: ApplicationFiled: December 18, 2013Publication date: April 17, 2014Applicant: MICROSOFT CORPORATIONInventors: Alexander Kolmykov-Zotov, Sashi Raghupathy, Xin Wang
-
Patent number: 8620084Abstract: 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.Type: GrantFiled: June 26, 2008Date of Patent: December 31, 2013Assignee: Microsoft CorporationInventors: Alexander Kolmykov-Zotov, Sashi Raghupathy, Xin Wang
-
Publication number: 20100169318Abstract: A user's experience with internet content may be given semantic meaning based upon extracting features of the content and creating kind classifications from the features. Kind classifications may be used to enrich a user's experience with internet content by providing meaningful navigation and discovery of information. As provided herein, a data stream (e.g., HTML, audio, video, unstructured data, etc.) is received, and features (e.g., text, phrases, titles, paragraphs, image data, etc.) may be extracted from the data stream. Kind classifications may be created based upon the extracted features. For example, a shirt image kind classification may be created based upon a button image feature, a collar image feature, and a sleeve image feature. The user's experience may be enriched by a presentation of actions allowing the user to view similar shirts, purchase the shirt, and/or discover other information relating to the shirt, for example.Type: ApplicationFiled: December 30, 2008Publication date: July 1, 2010Applicant: Microsoft CorporationInventors: Donald Thompson, Alexander Sasha Stojanovic, Alexander Kolmykov-Zotov
-
Patent number: 7679617Abstract: The present starburst target expansion technique connects targets to peripheral screen space to produce reasonably sized tiles for all targets including those that are located inside of a cluster. The resulting layout is characterized by lines escaping from the cluster center. By providing targets located inside a cluster with access to empty screen space, the present starburst target expansion technique is able to assign screen space to targets that remain small if expanded using the traditional Voronoi approach. If used on a device with limited input accuracy, such as a pen-based tablet or a touch screen-based kiosk system, target expansion via the starburst target expansion technique can lead to substantial performance improvements.Type: GrantFiled: February 15, 2007Date of Patent: March 16, 2010Assignee: Microsoft Corp.Inventors: Alexander Kolmykov-Zotov, Patrick Baudisch
-
Publication number: 20090324076Abstract: 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.Type: ApplicationFiled: June 26, 2008Publication date: December 31, 2009Applicant: Microsoft CorporationInventors: Alexander Kolmykov-Zotov, Sashi Raghupathy, Xin Wang
-
Patent number: 7499058Abstract: A system and method for performing ink related operations in a tree-based presentation system is described. Ink-related programmatical interfaces may relate to interactions with a stroke object, a stroke collection object, and ink input elements.Type: GrantFiled: April 24, 2006Date of Patent: March 3, 2009Assignee: Microsoft CorporationInventors: Shawn Van Ness, Sam George, Stefan Wick, Brian Ewanchuk, Todd Torset, Wayne Zeng, Xiao Tu, Koji Kato, Alexander Kolmykov-Zotov, Timothy Kannapel, Manoj Biswas, Kevin Welton, Richmond Lough, Chandramouli Kompella, Hongan Wang, Steven P. Dodge, Todd M. Landstad, Shiraz Somji, Vladimir V. Smirnov, Stephen A. Fisher, Rudolph Balaz, Michael Russell
-
Publication number: 20070198950Abstract: Upon detection of user input, a computing device (e.g., tablet PC, PDA, cellular device) may determine whether the input corresponds to a request to enhance elements of the user interface. In response to a positive determination, the computing device may magnify or otherwise modify the appearance of particular graphical elements of the interface to facilitate user interaction. The computing device identifies one or more graphical elements that are within a predefined proximity or area of the input location and displays an enlarged version of those elements to provide the user with a larger interaction area. Additionally, a computing device may clone (i.e., copy) the identified elements and enlarge the cloned elements at a specified region of the user interface. In another aspect, the computing device may magnify the entire area associated with the location of user input, rather than just the interactive elements of that predefined area.Type: ApplicationFiled: February 17, 2006Publication date: August 23, 2007Applicant: Microsoft CorporationInventors: Steven Dodge, Alexander Kolmykov-Zotov, Bryan Scott, Reed Townsend
-
Publication number: 20070192731Abstract: 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 UI 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.Type: ApplicationFiled: February 10, 2006Publication date: August 16, 2007Applicant: Microsoft CorporationInventors: Reed Townsend, Steven Dodge, Bryan Scott, Alexander Kolmykov-Zotov
-
Publication number: 20070153300Abstract: A system and process for ensuring the smooth flow of electronic ink is described. Dynamic rendering is give priority over other event handlers. Priority may be the use of one or more queues to order when events occur and may be performing dynamic rendering prior to other steps.Type: ApplicationFiled: March 2, 2007Publication date: July 5, 2007Applicant: MICROSOFT CORPORATIONInventors: Steve Dodge, Alexander Kolmykov-Zotov, Arin Goldberg, Brigette Krantz, Kyril Feldman, Manoj Biswas, Rudolph Balaz, Shenbagalakshmi Pichaiah
-
Publication number: 20070152976Abstract: 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.Type: ApplicationFiled: December 30, 2005Publication date: July 5, 2007Applicant: Microsoft CorporationInventors: Reed Townsend, Alexander Kolmykov-Zotov, Steven Dodge, Bryan Scott
-
Publication number: 20070121125Abstract: A system and process for ensuring the smooth flow of electronic ink is described. Dynamic rendering is give priority over other event handlers. Priority may be the use of one or more queues to order when events occur and may be performing dynamic rendering prior to other steps.Type: ApplicationFiled: January 24, 2007Publication date: May 31, 2007Applicant: MICROSOFT CORPORATIONInventors: Steve Dodge, Alexander Kolmykov-Zotov, Arin Goldberg, Brigette Krantz, Kyril Feldman, Manoj Biswas, Rudolph Balaz, Shenbagalakshmi Pichaiah