Patents by Inventor Pavan Kapanipathi
Pavan Kapanipathi 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: 11966706Abstract: A dialogue complexity assessment method, system, and computer program product including calculating a complexity utilizing domain-dependent terms and domain-independent terms of a dialogue, where the dialogue includes dialogue data from contact centers of service providers.Type: GrantFiled: August 4, 2022Date of Patent: April 23, 2024Assignee: DoorDash, Inc.Inventors: Biplav Srivastava, Qingzi Vera Liao, Pavan Kapanipathi Bangalore
-
Publication number: 20240078443Abstract: One or more computer processors improve knowledge base question answering (KBQA) model convergence and prediction performance by generalizing the KBQA model based on transfer learning.Type: ApplicationFiled: September 7, 2022Publication date: March 7, 2024Inventors: Srinivas Ravishankar, Dung Ngoc Thai, IBRAHIM ABDELAZIZ, Pavan Kapanipathi Bangalore, TAHIRA NASEEM, Achille Belly Fokoue-Nkoutche, NANDANA MIHINDUKULASOORIYA
-
Patent number: 11868716Abstract: One or more computer processors parse a received natural language question into an abstract meaning representation (AMR) graph. The one or more computer processors enrich the AMR graph into an extended AMR graph. The one or more computer processors transform the extended AMR graph into a query graph utilizing a path-based approach, wherein the query graph is a directed edge-labeled graph. The one or more computer processors generate one or more answers to the natural language question through one or more queries created utilizing the query graph.Type: GrantFiled: August 31, 2021Date of Patent: January 9, 2024Assignee: International Business Machines CorporationInventors: Srinivas Ravishankar, Pavan Kapanipathi Bangalore, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Dinesh Garg, Salim Roukos, Alexander Gray
-
Publication number: 20230229859Abstract: Methods, systems, and computer program products for zero-shot entity linking based on symbolic information are provided herein. A computer-implemented method includes obtaining a knowledge graph comprising a set of entities and a training dataset comprising text samples for at least a subset of the entities in the knowledge graph; training a machine learning model to map an entity mention substring of a given sample of text to one corresponding entity in the set of entities, wherein the machine learning model is trained using a multi-task machine learning framework using symbolic information extracted from the knowledge graph; and mapping an entity mention substring of a new sample of text to one of the entities in the set using the trained machine learning model.Type: ApplicationFiled: January 14, 2022Publication date: July 20, 2023Inventors: Dinesh Khandelwal, G P Shrivatsa Bhargav, Saswati Dana, Dinesh Garg, Pavan Kapanipathi Bangalore, Salim Roukos, Alexander Gray, L. Venkata Subramaniam
-
Patent number: 11640540Abstract: A method for assigning weights to a knowledge graph includes extracting information from a knowledge graph. The information including entities extracted from nodes of the knowledge graph and relations extracted from edges of the knowledge graph. A shortest path generator receives the extracted entities and relations, and potential assigned weights from a heuristic data repository. Weights for the edges of the knowledge graph are determined. The weights are assigned to the edges of the knowledge graph.Type: GrantFiled: March 10, 2020Date of Patent: May 2, 2023Assignee: International Business Machines CorporationInventors: Kshitij Fadnis, Kartik Talamadupula, Pavan Kapanipathi Bangalore, Achille Belly Fokoue-Nkoutche
-
Publication number: 20230100883Abstract: To improve the technological process of computerized answering of logical queries over incomplete knowledge bases, obtain a first order logic query; with a trained, computerized neural network, convert the first order logic query into a logic embedding; and answer the first order logic query using the logic embedding.Type: ApplicationFiled: September 28, 2021Publication date: March 30, 2023Inventors: Francois Pierre Luus, Prithviraj Sen, Ryan Nelson Riegel, Ndivhuwo Makondo, Thabang Doreen Lebese, Naweed Aghmad Khan, Pavan Kapanipathi
-
Publication number: 20230060589Abstract: One or more computer processors parse a received natural language question into an abstract meaning representation (AMR) graph. The one or more computer processors enrich the AMR graph into an extended AMR graph. The one or more computer processors transform the extended AMR graph into a query graph utilizing a path-based approach, wherein the query graph is a directed edge-labeled graph. The one or more computer processors generate one or more answers to the natural language question through one or more queries created utilizing the query graph.Type: ApplicationFiled: August 31, 2021Publication date: March 2, 2023Inventors: Srinivas Ravishankar, Pavan Kapanipathi Bangalore, IBRAHIM ABDELAZIZ, NANDANA MIHINDUKULASOORIYA, Dinesh Garg, Salim Roukos, Alexander Gray
-
Publication number: 20220382997Abstract: A dialogue complexity assessment method, system, and computer program product including calculating a complexity utilizing domain-dependent terms and domain-independent terms of a dialogue, where the dialogue includes dialogue data from contact centers of service providers.Type: ApplicationFiled: August 4, 2022Publication date: December 1, 2022Applicant: DoorDash, Inc.Inventors: Biplav Srivastava, Qingzi Vera Liao, Pavan Kapanipathi Bangalore
-
Patent number: 11443121Abstract: A dialogue complexity assessment method, system, and computer program product including calculating a complexity utilizing domain-dependent terms and domain-independent terms of a dialogue, where the dialogue includes dialogue data from contact centers of service providers.Type: GrantFiled: October 22, 2019Date of Patent: September 13, 2022Assignee: DoorDash, Inc.Inventors: Biplav Srivastava, Qingzi Vera Liao, Pavan Kapanipathi Bangalore
-
Patent number: 11429876Abstract: One embodiment of the invention provides a method for natural language processing (NLP). The method comprises extracting knowledge outside of text content of a NLP instance by extracting a set of subgraphs from a knowledge graph associated with the text content. The set of subgraphs comprises the knowledge. The method further comprises encoding the knowledge with the text content into a fixed size graph representation by filtering and encoding the set of subgraphs. The method further comprises applying a text embedding algorithm to the text content to generate a fixed size text representation, and classifying the text content based on the fixed size graph representation and the fixed size text representation.Type: GrantFiled: March 10, 2020Date of Patent: August 30, 2022Assignee: International Business Machines CorporationInventors: Pavan Kapanipathi Bangalore, Kartik Talamadupula, Veronika Thost, Siva Sankalp Patel, Ibrahim Abdelaziz, Avinash Balakrishnan, Maria Chang, Kshitij Fadnis, Chulaka Gunasekara, Bassem Makni, Nicholas Mattei, Achille Belly Fokoue-Nkoutche
-
Publication number: 20220129770Abstract: A computer-implemented method according to one embodiment includes identifying a natural language query; translating the natural language query into an intermediate representation; converting the intermediate representation into one or more query triples; and performing relation linking between each of the one or more query triples and a plurality of knowledge base triples.Type: ApplicationFiled: October 23, 2020Publication date: April 28, 2022Inventors: Nandana Mihindukulasooriya, Gaetano Rossiello, Alfio Massimiliano Gliozzo, Pavan Kapanipathi Bangalore, Salim Roukos
-
Publication number: 20210287102Abstract: A method for assigning weights to a knowledge graph includes extracting information from a knowledge graph. The information including entities extracted from nodes of the knowledge graph and relations extracted from edges of the knowledge graph. A shortest path generator receives the extracted entities and relations, and potential assigned weights from a heuristic data repository. Weights for the edges of the knowledge graph are determined. The weights are assigned to the edges of the knowledge graph.Type: ApplicationFiled: March 10, 2020Publication date: September 16, 2021Inventors: Kshitij Fadnis, Kartik Talamadupula, Pavan Kapanipathi Bangalore, Achille Belly Fokoue-Nkoutche
-
Publication number: 20210287103Abstract: One embodiment of the invention provides a method for natural language processing (NLP). The method comprises extracting knowledge outside of text content of a NLP instance by extracting a set of subgraphs from a knowledge graph associated with the text content. The set of subgraphs comprises the knowledge. The method further comprises encoding the knowledge with the text content into a fixed size graph representation by filtering and encoding the set of subgraphs. The method further comprises applying a text embedding algorithm to the text content to generate a fixed size text representation, and classifying the text content based on the fixed size graph representation and the fixed size text representation.Type: ApplicationFiled: March 10, 2020Publication date: September 16, 2021Inventors: Pavan Kapanipathi Bangalore, Kartik Talamadupula, Veronika Thost, Siva Sankalp Patel, Ibrahim Abdelaziz, Avinash Balakrishnan, Maria Chang, Kshitij Fadnis, Chulaka Gunasekara, Bassem Makni, Nicholas Mattei, Achille Belly Fokoue-Nkoutche
-
Patent number: 10565316Abstract: A dialogue complexity assessment method, system, and computer program product for introducing the notion of dialogue complexity to understand and compare dialogues in a repository, calculating the dialogue complexity, use the dialogue complexity to understand customer interactions in a variety of domains using public and proprietary data, and demonstrate the dialogue complexity usage to improve a service management operation.Type: GrantFiled: July 30, 2018Date of Patent: February 18, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Biplav Srivastava, Qingzi Vera Liao, Pavan Kapanipathi Bangalore
-
Publication number: 20200050666Abstract: A dialogue complexity assessment method, system, and computer program product including calculating a complexity utilizing domain-dependent terms and domain-independent terms of a dialogue, where the dialogue includes dialogue data from contact centers of service providers.Type: ApplicationFiled: October 22, 2019Publication date: February 13, 2020Inventors: Biplav Srivastava, Qingzi Vera Liao, Pavan Kapanipathi Bangalore
-
Patent number: 10430805Abstract: Enriching trajectory data from a device may include determining, using a processor, enrichment data items related to points of presence within trajectory data. The enrichment data items may be retrieved from a data source. Enriching trajectory data may also include determining, using the processor, ranking metrics for the enrichment data items and ranking, using the processor, the enrichment data items according to the ranking metrics. One or more ranked enrichment data items, in association with the related point of presence of the trajectory data, may be provided to a device using the processor.Type: GrantFiled: October 30, 2015Date of Patent: October 1, 2019Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Joakim Soderberg, Edwin A. Heredia, Pavan Kapanipathi, Glenn Algie, Alan Messer
-
Publication number: 20180365213Abstract: A dialogue complexity assessment method, system, and computer program product for introducing the notion of dialogue complexity to understand and compare dialogues in a repository, calculating the dialogue complexity, use the dialogue complexity to understand customer interactions in a variety of domains using public and proprietary data, and demonstrate the dialogue complexity usage to improve a service management operation.Type: ApplicationFiled: July 30, 2018Publication date: December 20, 2018Inventors: Biplav Srivastava, Qingzi Vera Liao, Pavan Kapanipathi Bangalore
-
Publication number: 20180314685Abstract: A dialogue complexity assessment method, system, and computer program product for introducing the notion of dialogue complexity to understand and compare dialogues in a repository, calculating the dialogue complexity, use the dialogue complexity to understand customer interactions in a variety of domains using public and proprietary data, and demonstrate the dialogue complexity usage to improve a service management operation.Type: ApplicationFiled: April 28, 2017Publication date: November 1, 2018Inventors: Biplav Srivastava, Qingzi Vera Liao, Pavan Kapanipathi Bangalore
-
Patent number: 10114816Abstract: A dialogue complexity assessment method, system, and computer program product for introducing the notion of dialogue complexity to understand and compare dialogues in a repository, calculating the dialogue complexity, use the dialogue complexity to understand customer interactions in a variety of domains using public and proprietary data, and demonstrate the dialogue complexity usage to improve a service management operation.Type: GrantFiled: April 28, 2017Date of Patent: October 30, 2018Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Biplav Srivastava, Qingzi Vera Liao, Pavan Kapanipathi Bangalore
-
Publication number: 20160170994Abstract: Enriching trajectory data from a device may include determining, using a processor, enrichment data items related to points of presence within trajectory data. The enrichment data items may be retrieved from a data source. Enriching trajectory data may also include determining, using the processor, ranking metrics for the enrichment data items and ranking, using the processor, the enrichment data items according to the ranking metrics. One or more ranked enrichment data items, in association with the related point of presence of the trajectory data, may be provided to a device using the processor.Type: ApplicationFiled: October 30, 2015Publication date: June 16, 2016Inventors: Joakim Soderberg, Edwin A. Heredia, Pavan Kapanipathi, Glenn Algie, Alan Messer