Patents by Inventor Margaret Helen Szymanski
Margaret Helen Szymanski 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: 11238234Abstract: In one general aspect, a computer-implemented method includes identifying current choices with different verbosity levels for a current turn in a conversation; normalizing multi-dimensional verbosity vectors for each of the current choices to obtain a normalized value for each of the current choices; determining a state definition for the current turn in the conversation, utilizing the normalized values for each of the current choices; providing the state definition for the current turn in the conversation and the normalized values for each of the current choices to a trained reinforcement learning module; receiving, from the trained reinforcement learning module, a score associated with each of the current choices for the current turn in the conversation; and selecting one of the current choices to be entered for the current turn in the conversation, based on the score associated with each of the current choices for the current turn in the conversation.Type: GrantFiled: September 11, 2019Date of Patent: February 1, 2022Assignee: International Business Machines CorporationInventors: Shun Jiang, Robert John Moore, Margaret Helen Szymanski, Lei Huang, Guangjie Ren, Peifeng Yin
-
Patent number: 11138978Abstract: A method and system of automatically identifying topics of a conversation are provided. An electronic data package comprising a sequence of utterances between conversation entities is received by a computing device. Each utterance is classified to a corresponding social action. One or more utterances in the sequence are grouped into a segment based on a deep learning model. A similarity of topics between adjacent segments is determined. Upon determining that the similarity is above a predetermined threshold, the adjacent segments are grouped together. A transcript of the conversation including the grouping of the adjacent segments is stored in a memory.Type: GrantFiled: July 24, 2019Date of Patent: October 5, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Margaret Helen Szymanski, Lei Huang, Robert John Moore, Raphael Arar, Shun Jiang, Guangjie Ren, Eric Liu, Pawan Chowdhary, Chung-hao Tan, Sunhwan Lee
-
Publication number: 20210073337Abstract: In one general aspect, a computer-implemented method includes identifying current choices with different verbosity levels for a current turn in a conversation; normalizing multi-dimensional verbosity vectors for each of the current choices to obtain a normalized value for each of the current choices; determining a state definition for the current turn in the conversation, utilizing the normalized values for each of the current choices; providing the state definition for the current turn in the conversation and the normalized values for each of the current choices to a trained reinforcement learning module; receiving, from the trained reinforcement learning module, a score associated with each of the current choices for the current turn in the conversation; and selecting one of the current choices to be entered for the current turn in the conversation, based on the score associated with each of the current choices for the current turn in the conversation.Type: ApplicationFiled: September 11, 2019Publication date: March 11, 2021Inventors: Shun Jiang, Robert John Moore, Margaret Helen Szymanski, Lei Huang, Guangjie Ren, Peifeng Yin
-
Publication number: 20210027783Abstract: A method and system of automatically identifying topics of a conversation are provided. An electronic data package comprising a sequence of utterances between conversation entities is received by a computing device. Each utterance is classified to a corresponding social action. One or more utterances in the sequence are grouped into a segment based on a deep learning model. A similarity of topics between adjacent segments is determined. Upon determining that the similarity is above a predetermined threshold, the adjacent segments are grouped together. A transcript of the conversation including the grouping of the adjacent segments is stored in a memory.Type: ApplicationFiled: July 24, 2019Publication date: January 28, 2021Inventors: Margaret Helen Szymanski, Lei Huang, Robert John Moore, Raphael Arar, Shun Jiang, Guangjie Ren, Eric Liu, Pawan Chowdhary, Chung-hao Tan, Sunhwan Lee
-
Patent number: 9330422Abstract: The present disclosure provides a system that allows for the real-time and online monitoring of the exchanges between customers and a CRM team over social media. While crawling all messages exchanged over the social media by customers and CRM team, the system aggregates related messages exchanged between a given customer and the CRM team into a conversation. The system includes a linguistic framework for the analysis of conversations (based on the two linguistic theories of dialog acts and conversation analysis) to label the nature of the messages in a conversation or thread.Type: GrantFiled: March 15, 2013Date of Patent: May 3, 2016Assignee: XEROX CORPORATIONInventors: Julien Jean Lucien Bourdaillet, Wei Peng, Tong Sun, Margaret Helen Szymanski
-
Publication number: 20140280621Abstract: The present disclosure provides a system that allows for the real-time and online monitoring of the exchanges between customers and a CRM team over social media. While crawling all messages exchanged over the social media by customers and CRM team, the system aggregates related messages exchanged between a given customer and the CRM team into a conversation. The system includes a linguistic framework for the analysis of conversations (based on the two linguistic theories of dialog acts and conversation analysis) to label the nature of the messages in a conversation or thread.Type: ApplicationFiled: March 15, 2013Publication date: September 18, 2014Applicants: PALO ALTO RESEARCH CENTER INCORPORATED, XEROX CORPORATIONInventors: Julien Jean Lucien Bourdaillet, Wei Peng, Tong Sun, Margaret Helen Szymanski
-
Publication number: 20090313553Abstract: A system and method for providing multimedia content between a plurality of user terminals is presented. A first multimedia presentation on a first user terminal is selected by a first user. Data corresponding to the first multimedia presentation is transmitted to a second user terminal. Data is received corresponding to a second multimedia presentation from the second user terminal by the first user terminal. The first multimedia presentation or the second multimedia presentation is displayed on the first user terminal and the second user terminal based on, respectively, a first profile of the first user terminal and a second profile of the second user terminal.Type: ApplicationFiled: August 10, 2009Publication date: December 17, 2009Applicant: XEROX CORPORATIONInventors: James Douglass Thornton, Rebecca Elizabeth Grinter, Paul Masami Aoki, Allison Gyle Woodruff, Margaret Helen Szymanski
-
Publication number: 20090246744Abstract: A method of automatically generating personalized text for teaching a student to learn to read. Based upon inputs of the students reading ability/level, either from a self assessment or teacher input and input of personal data, the system automatically searches selected libraries and chooses appropriate text and modifies the text for vocabulary and topics of character identification of personal interest to the student. An optional function of previewing by one of the student's teacher, parent or advocate is included. The system generates a local repository of generated text associated with a particular student.Type: ApplicationFiled: March 25, 2008Publication date: October 1, 2009Applicants: Xerox Corporation, Palo Alto Research Center IncorporatedInventors: Robert M. Lofthus, Kristine A. German, Frederique Segond, Tracy Holloway King, Marilyn Whalen, Luke Plurkowski, Margaret Helen Szymanski, Qingfeng Huang
-
Patent number: 7574474Abstract: At least one multimedia presentation is selected by a user of a first device, accessed from a storage source, and presented to the user. Simultaneously, information is transmitted to at least a second device to cause the selected multimedia presentation to be presented by the at least second device without the at least second device receiving input from a second user. Continuous media streams from the first user may be captured and transmitted to the second device. The presenting of the multimedia presentation on the first device is coordinated with the presenting of the multimedia presentation on the second device. The presenting of the captured media streams on the second device is coordinated with the capturing of those streams and the presenting of the multimedia presentation on the second device. Users may individually control the multimedia presentations and the captured media streams.Type: GrantFiled: September 14, 2001Date of Patent: August 11, 2009Assignee: Xerox CorporationInventors: James Douglass Thornton, Rebecca Elizabeth Grinter, Paul Masami Aoki, Allison Gyle Woodruff, Margaret Helen Szymanski
-
Publication number: 20030056220Abstract: A user of a first device may select at least one multimedia presentation. Based on this selection, the multimedia presentation is accessed from a storage source and presented to the user. Simultaneously, information is transmitted to at least a second device that causes the selected multimedia presentation to be presented by the at least second device without the at least second device receiving input from a second user. Continuous media streams from the first user may be captured and transmitted to the second device(s). The presenting of the multimedia presentation on the first device are coordinated with the presenting of the multimedia presentation on the second device(s). The presenting of the captured media streams on the second device(s) are coordinated with the capturing of those streams and the presenting of the multimedia presentation on the second device(s). Users may control the multimedia presentations and the captured media streams.Type: ApplicationFiled: September 14, 2001Publication date: March 20, 2003Inventors: James Douglass Thornton, Rebecca Elizabeth Grinter, Paul Masami Aoki, Allison Gyle Woodruff, Margaret Helen Szymanski