Patents by Inventor Yeon-Sup Lim
Yeon-Sup Lim 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: 11551143Abstract: A computer-implemented method for generating and deploying a reinforced learning model to train a chatbot. The method includes selecting a plurality of conversations, wherein each conversation includes an agent and a user. The method includes identifying, in each of the conversations, a set of turns and on or more topics. The method further includes associating one or more topics to each turn of the set of turns. The method includes, generating a conversation flow for each conversation, wherein the conversation flow identifies a sequence of the topics. The method includes applying an outcome score to each conversation. The method includes creating a reinforced learning (RL) model, wherein the RL model includes a Markov is based on the conversation flow of each conversation and the outcome score of each conversation. The method includes deploying the RL model, wherein the deploying includes sending the RL model to a chatbot.Type: GrantFiled: November 21, 2019Date of Patent: January 10, 2023Assignee: International Business Machines CorporationInventors: Raghu Kiran Ganti, Mudhakar Srivatsa, Shreeranjani Srirangamsridharan, Yeon-sup Lim, Linsong Chu
-
Patent number: 11182415Abstract: Embodiments of the invention include method, systems and computer program products for document vectorization. Aspects include receiving, by a processor, a plurality of documents each having a plurality of word. The processor utilizing a vector embeddings engine generates a vector to represent each of the plurality of words in the plurality of documents. An image representation for each document in the plurality of documents is created and a word probability for each of the plurality of words in the plurality of documents is generated. A position for each word probability is determined in the image based on the vector associated with each word and a compression operation on the images is performed to produce a compact representation for the plurality of documents.Type: GrantFiled: July 11, 2018Date of Patent: November 23, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Shreeranjani Srirangamsridharan, Raghu Kiran Ganti, Mudhakar Srivatsa, Yeon-Sup Lim
-
Publication number: 20210158203Abstract: A computer-implemented method for generating and deploying a reinforced learning model to train a chatbot. The method includes selecting a plurality of conversations, wherein each conversation includes an agent and a user. The method includes identifying, in each of the conversations, a set of turns and on or more topics. The method further includes associating one or more topics to each turn of the set of turns. The method includes, generating a conversation flow for each conversation, wherein the conversation flow identifies a sequence of the topics. The method includes applying an outcome score to each conversation. The method includes creating a reinforced learning (RL) model, wherein the RL model includes a Markov is based on the conversation flow of each conversation and the outcome score of each conversation. The method includes deploying the RL model, wherein the deploying includes sending the RL model to a chatbot.Type: ApplicationFiled: November 21, 2019Publication date: May 27, 2021Inventors: RAGHU KIRAN GANTI, MUDHAKAR SRIVATSA, Shreeranjani Srirangamsridharan, Yeon-sup Lim, Linsong Chu
-
Publication number: 20210103608Abstract: Embodiments for providing rare topic detection using hierarchical topic modeling by a processor. A hierarchical topic model may be learned from one or more data sources. One or more dominant words in a selected cluster may be iteratively removed using the hierarchical topic model. The dominant words may relate to one or more primary topics of the cluster. The learned hierarchical topic model may be seeded with one or more words, n-grams, phrases, text snippets, or a combination thereof to evolve the hierarchical topic model and the removed domain words are reinstated upon completion of the seeding.Type: ApplicationFiled: October 8, 2019Publication date: April 8, 2021Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Raghu GANTI, Mudhakar SRIVATSA, Shreeranjani SRIRANGAMSRIDHARAN, Yeon-sup LIM, Dakshi AGRAWAL
-
Patent number: 10922486Abstract: A parse tree corresponding to a portion of narrative text is constructed. The parse tree includes a data structure representing a syntactic structure of the portion of narrative text as a set of tokens according to a grammar. Using a token in the parse tree as a focus word, a context window comprising a set of words within a specified distance from the focus word is generated, the distance determined according to a number of links of the parse tree separating the focus word and a context word in the set of words. A weight is generated for the focus word and the context word. Using the weight, a first vector representation of a first word is generated, the first word being within a second portion of narrative text.Type: GrantFiled: March 13, 2019Date of Patent: February 16, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Mudhakar Srivatsa, Raghu Kiran Ganti, Yeon-sup Lim, Shreeranjani Srirangamsridharan, Antara Palit
-
Patent number: 10785163Abstract: Various embodiments are provided for managing queuing policies in a computing environment. Data packets may be classified into one of a plurality of queues based on information extracted from one or more multipath data flows. The data packets in the plurality of queues may be scheduled and sent according to one or more multipath data flows.Type: GrantFiled: February 27, 2019Date of Patent: September 22, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Erich Nahum, Thai Franck Le, Yeon-sup Lim
-
Publication number: 20200293614Abstract: A parse tree corresponding to a portion of narrative text is constructed. The parse tree includes a data structure representing a syntactic structure of the portion of narrative text as a set of tokens according to a grammar. Using a token in the parse tree as a focus word, a context window comprising a set of words within a specified distance from the focus word is generated, the distance determined according to a number of links of the parse tree separating the focus word and a context word in the set of words. A weight is generated for the focus word and the context word. Using the weight, a first vector representation of a first word is generated, the first word being within a second portion of narrative text.Type: ApplicationFiled: March 13, 2019Publication date: September 17, 2020Applicant: International Business Machines CorporationInventors: MUDHAKAR SRIVATSA, RAGHU KIRAN GANTI, Yeon-sup Lim, Shreeranjani Srirangamsridharan, Antara Palit
-
Publication number: 20200274819Abstract: Various embodiments are provided for managing queuing policies in a computing environment. Data packets may be classified into one of a plurality of queues based on information extracted from one or more multipath data flows. The data packets in the plurality of queues may be scheduled and sent according to one or more multipath data flows.Type: ApplicationFiled: February 27, 2019Publication date: August 27, 2020Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Erich NAHUM, Thai Franck LE, Yeon-sup LIM
-
Publication number: 20200019618Abstract: Embodiments of the invention include method, systems and computer program products for document vectorization. Aspects include receiving, by a processor, a plurality of documents each having a plurality of word. The processor utilizing a vector embeddings engine generates a vector to represent each of the plurality of words in the plurality of documents. An image representation for each document in the plurality of documents is created and a word probability for each of the plurality of words in the plurality of documents is generated. A position for each word probability is determined in the image based on the vector associated with each word and a compression operation on the images is performed to produce a compact representation for the plurality of documents.Type: ApplicationFiled: July 11, 2018Publication date: January 16, 2020Inventors: Shreeranjani Srirangamsridharan, Raghu Kiran Ganti, Mudhakar Srivatsa, Yeon-Sup Lim