Patents by Inventor Stefan Krawczyk

Stefan Krawczyk 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).

  • Publication number: 20210232761
    Abstract: Systems and methods are presented for providing improved machine performance in natural language processing. In some example embodiments, an API module is presented that is configured to drive processing of a system architecture for natural language processing. Aspects of the present disclosure allow for a natural language model to classify documents while other documents are being retrieved in real time. The natural language model and the documents are configured to be stored in a stateless format, which also allows for additional functions to be performed on the documents while the natural language model is used to continue classifying other documents.
    Type: Application
    Filed: December 22, 2020
    Publication date: July 29, 2021
    Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Jason Brenier, Paul A. Tepper, Jessica D. Long, James B. Robinson, Aneesh Nair, Michelle Casbon, Stefan Krawczyk
  • Publication number: 20210232760
    Abstract: Methods, apparatuses and computer readable medium are presented for generating a natural language model. A method for generating a natural language model comprises: selecting from a pool of documents, a first set of documents to be annotated; receiving annotations of the first set of documents elicited by first human readable prompts; training a natural language model using the annotated first set of documents; determining documents in the pool having uncertain natural language processing results according to the trained natural language model and/or the received annotations; selecting from the pool of documents, a second set of documents to be annotated comprising documents having uncertain natural language processing results; receiving annotations of the second set of documents elicited by second human readable prompts; and retraining a natural language model using the annotated second set of documents.
    Type: Application
    Filed: December 11, 2020
    Publication date: July 29, 2021
    Inventors: Robert J. Munro, Schuyler D. Erle, Jason Brenier, Paul A. Tepper, Tripti Saxena, Gary C. King, Jessica D. Long, Brendan D. Callahan, Tyler J. Schnoebelen, Stefan Krawczyk, Veena Basavaraj
  • Publication number: 20210157984
    Abstract: Systems, methods, and apparatuses are presented for a novel natural language tokenizer and tagger. In some embodiments, a method for tokenizing text for natural language processing comprises: generating from a pool of documents, a set of statistical models comprising one or more entries each indicating a likelihood of appearance of a character/letter sequence in the pool of documents; receiving a set of rules comprising rules that identify character/letter sequences as valid tokens; transforming one or more entries in the statistical models into new rules that are added to the set of rules when the entries indicate a high likelihood; receiving a document to be processed; dividing the document to be processed into tokens based on the set of statistical models and the set of rules, wherein the statistical models are applied where the rules fail to unambiguously tokenize the document; and outputting the divided tokens for natural language processing.
    Type: Application
    Filed: March 27, 2020
    Publication date: May 27, 2021
    Inventors: Robert J. Munro, Rob Voigt, Schuyler D. Erle, Brendan D. Callahan, Gary C. King, Jessica D. Long, Jason Brenier, Tripti Saxena, Stefan Krawczyk
  • Publication number: 20210081611
    Abstract: Methods, apparatuses, and systems are presented for generating natural language models using a novel system architecture for feature extraction. A method for extracting features for natural language processing comprises: accessing one or more tokens generated from a document to be processed; receiving one or more feature types defined by user; receiving selection of one or more feature types from a plurality of system-defined and user-defined feature types, wherein each feature type comprises one or more rules for generating features; receiving one or more parameters for the selected feature types, wherein the one or more rules for generating features are defined at least in part by the parameters; generating features associated with the document to be processed based on the selected feature types and the received parameters; and outputting the generated features in a format common among all feature types.
    Type: Application
    Filed: April 29, 2020
    Publication date: March 18, 2021
    Applicant: Singapore Biotech PTE. LTD.
    Inventors: Robert J. Munro, Schuyler D. Erle, Tyler J. Schnoebelen, Brendan D. Callahan, Jessica D. Long, Gary C. King, Paul A. Tepper, Jason A. Brenier, Stefan Krawczyk
  • Publication number: 20200234002
    Abstract: Methods, apparatuses and computer readable medium are presented for generating a natural language model. A method for generating a natural language model comprises: selecting from a pool of documents, a first set of documents to be annotated; receiving annotations of the first set of documents elicited by first human readable prompts; training a natural language model using the annotated first set of documents; determining documents in the pool having uncertain natural language processing results according to the trained natural language model and/or the received annotations; selecting from the pool of documents, a second set of documents to be annotated comprising documents having uncertain natural language processing results; receiving annotations of the second set of documents elicited by second human readable prompts; and retraining a natural language model using the annotated second set of documents.
    Type: Application
    Filed: November 21, 2018
    Publication date: July 23, 2020
    Inventors: Robert J. Munro, Schuyler D. Erle, Jason Brenier, Paul A. Tepper, Tripti Saxena, Gary C. King, Jessica D. Long, Brendan D. Callahan, Tyler J. Schnoebelen, Stefan Krawczyk, Veena Basavaraj
  • Publication number: 20190377788
    Abstract: Methods, apparatuses, and systems are presented for generating natural language models using a novel system architecture for feature extraction. A method for extracting features for natural language processing comprises: accessing one or more tokens generated from a document to be processed; receiving one or more feature types defined by user; receiving selection of one or more feature types from a plurality of system-defined and user-defined feature types, wherein each feature type comprises one or more rules for generating features; receiving one or more parameters for the selected feature types, wherein the one or more rules for generating features are defined at least in part by the parameters; generating features associated with the document to be processed based on the selected feature types and the received parameters; and outputting the generated features in a format common among all feature types.
    Type: Application
    Filed: January 2, 2019
    Publication date: December 12, 2019
    Applicant: AIPARC HOLDINGS PTE. LTD.
    Inventors: Robert J. Munro, Schuyler D. Erle, Tyler J. Schnoebelen, Brendan D. Callahan, Jessica D. Long, Gary C. King, Paul A. Tepper, Jason A. Brenier, Stefan Krawczyk
  • Publication number: 20190243886
    Abstract: Systems and methods are presented for providing improved machine performance in natural language processing. In some example embodiments, an API module is presented that is configured to drive processing of a system architecture for natural language processing. Aspects of the present disclosure allow for a natural language model to classify documents while other documents are being retrieved in real time. The natural language model and the documents are configured to be stored in a stateless format, which also allows for additional functions to be performed on the documents while the natural language model is used to continue classifying other documents.
    Type: Application
    Filed: September 7, 2018
    Publication date: August 8, 2019
    Applicant: Idibon, Inc.
    Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Jason Brenier, Paul A. Tepper, Jessica D. Long, James B. Robinson, Aneesh Nair, Michelle Casbon, Stefan Krawczyk
  • Publication number: 20190205377
    Abstract: Systems, methods, and apparatuses are presented for a novel natural language tokenizer and tagger. In some embodiments, a method for tokenizing text for natural language processing comprises: generating from a pool of documents, a set of statistical models comprising one or more entries each indicating a likelihood of appearance of a character/letter sequence in the pool of documents; receiving a set of rules comprising rules that identify character/letter sequences as valid tokens; transforming one or more entries in the statistical models into new rules that are added to the set of rules when the entries indicate a high likelihood; receiving a document to be processed; dividing the document to be processed into tokens based on the set of statistical models and the set of rules, wherein the statistical models are applied where the rules fail to unambiguously tokenize the document; and outputting the divided tokens for natural language processing.
    Type: Application
    Filed: August 6, 2018
    Publication date: July 4, 2019
    Applicant: Idibon, Inc.
    Inventors: Robert J. Munro, Rob Voigt, Schuyler D. Erle, Brendan D. Callahan, Gary C. King, Jessica D. Long, Jason Brenier, Tripti Saxena, Stefan Krawczyk
  • Publication number: 20180157636
    Abstract: Methods, apparatuses, and systems are presented for generating natural language models using a novel system architecture for feature extraction. A method for extracting features for natural language processing comprises: accessing one or more tokens generated from a document to be processed; receiving one or more feature types defined by user; receiving selection of one or more feature types from a plurality of system-defined and user-defined feature types, wherein each feature type comprises one or more rules for generating features; receiving one or more parameters for the selected feature types, wherein the one or more rules for generating features are defined at least in part by the parameters; generating features associated with the document to be processed based on the selected feature types and the received parameters; and outputting the generated features in a format common among all feature types.
    Type: Application
    Filed: November 15, 2017
    Publication date: June 7, 2018
    Applicant: Idibon, Inc.
    Inventors: Robert J. Munro, Schuyler D. Erle, Tyler j. Schnoebelen, Brendan D. Callahan, Jessica D. Long, Gary C. King, Paul A. Tepper, Jason A. Brenier, Stefan Krawczyk
  • Patent number: 9965458
    Abstract: Systems, methods, and apparatuses are presented for a novel natural language tokenizer and tagger. In some embodiments, a method for tokenizing text for natural language processing comprises: generating from a pool of documents, a set of statistical models comprising one or more entries each indicating a likelihood of appearance of a character/letter sequence in the pool of documents; receiving a set of rules comprising rules that identify character/letter sequences as valid tokens; transforming one or more entries in the statistical models into new rules that are added to the set of rules when the entries indicate a high likelihood; receiving a document to be processed; dividing the document to be processed into tokens based on the set of statistical models and the set of rules, wherein the statistical models are applied where the rules fail to unambiguously tokenize the document; and outputting the divided tokens for natural language processing.
    Type: Grant
    Filed: December 9, 2015
    Date of Patent: May 8, 2018
    Assignee: Sansa AI Inc.
    Inventors: Robert J. Munro, Rob Voigt, Schuyler D. Erle, Brendan D. Callahan, Gary C. King, Jessica D. Long, Jason Brenier, Tripti Saxena, Stefan Krawczyk
  • Publication number: 20180095946
    Abstract: Systems, methods, and apparatuses are presented for a novel natural language tokenizer and tagger. In some embodiments, a method for tokenizing text for natural language processing comprises: generating from a pool of documents, a set of statistical models comprising one or more entries each indicating a likelihood of appearance of a character/letter sequence in the pool of documents; receiving a set of rules comprising rules that identify character/letter sequences as valid tokens; transforming one or more entries in the statistical models into new rules that are added to the set of rules when the entries indicate a high likelihood; receiving a document to be processed; dividing the document to be processed into tokens based on the set of statistical models and the set of rules, wherein the statistical models are applied where the rules fail to unambiguously tokenize the document; and outputting the divided tokens for natural language processing.
    Type: Application
    Filed: May 16, 2017
    Publication date: April 5, 2018
    Applicant: Idibon, Inc.
    Inventors: Robert Munro, Rob Voigt, Schuyler D. Erle, Brendan D. Callahan, Gary C. King, Jessica D. Long, Jason Brenier, Tripti Saxena, Stefan Krawczyk
  • Publication number: 20160162457
    Abstract: Methods, apparatuses and computer readable medium are presented for generating a natural language model. A method for generating a natural language model comprises: selecting from a pool of documents, a first set of documents to be annotated; receiving annotations of the first set of documents elicited by first human readable prompts; training a natural language model using the annotated first set of documents; determining documents in the pool having uncertain natural language processing results according to the trained natural language model and/or the received annotations; selecting from the pool of documents, a second set of documents to be annotated comprising documents having uncertain natural language processing results; receiving annotations of the second set of documents elicited by second human readable prompts; and retraining a natural language model using the annotated second set of documents.
    Type: Application
    Filed: December 9, 2015
    Publication date: June 9, 2016
    Applicant: Idibon, Inc.
    Inventors: Robert J. Munro, Schuyler D. Erle, Jason Brenier, Paul A. Tepper, Tripti Saxena, Gary C. King, Jessica D. Long, Brendan D. Callahan, Tyler J. Schnoebelen, Stefan Krawczyk, Veena Basavaraj
  • Publication number: 20160162569
    Abstract: Systems and methods are presented for providing improved machine performance in natural language processing. In some example embodiments, an API module is presented that is configured to drive processing of a system architecture for natural language processing. Aspects of the present disclosure allow for a natural language model to classify documents while other documents are being retrieved in real time. The natural language model and the documents are configured to be stored in a stateless format, which also allows for additional functions to be performed on the documents while the natural language model is used to continue classifying other documents.
    Type: Application
    Filed: December 9, 2015
    Publication date: June 9, 2016
    Applicant: Idibon, Inc.
    Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Jason Brenier, Paul A. Tepper, Jessica D. Long, James B. Robinson, Aneesh Nair, Michelle Casbon, Stefan Krawczyk
  • Publication number: 20160162467
    Abstract: Methods, apparatuses, and systems are presented for generating natural language models using a novel system architecture for feature extraction. A method for extracting features for natural language processing comprises: accessing one or more tokens generated from a document to be processed; receiving one or more feature types defined by user; receiving selection of one or more feature types from a plurality of system-defined and user-defined feature types, wherein each feature type comprises one or more rules for generating features; receiving one or more parameters for the selected feature types, wherein the one or more rules for generating features are defined at least in part by the parameters; generating features associated with the document to be processed based on the selected feature types and the received parameters; and outputting the generated features in a format common among all feature types.
    Type: Application
    Filed: December 9, 2015
    Publication date: June 9, 2016
    Applicant: Idibon, Inc.
    Inventors: Robert J. Munro, Schuyler D. Erle, Tyler J. Schnoebelen, Brendan D. Callahan, Jessica D. Long, Gary C. King, Paul A. Tepper, Jason Brenier, Stefan Krawczyk
  • Publication number: 20160162466
    Abstract: Systems, methods, and apparatuses are presented for a novel natural language tokenizer and tagger. In some embodiments, a method for tokenizing text for natural language processing comprises: generating from a pool of documents, a set of statistical models comprising one or more entries each indicating a likelihood of appearance of a character/letter sequence in the pool of documents; receiving a set of rules comprising rules that identify character/letter sequences as valid tokens; transforming one or more entries in the statistical models into new rules that are added to the set of rules when the entries indicate a high likelihood; receiving a document to be processed; dividing the document to be processed into tokens based on the set of statistical models and the set of rules, wherein the statistical models are applied where the rules fail to unambiguously tokenize the document; and outputting the divided tokens for natural language processing.
    Type: Application
    Filed: December 9, 2015
    Publication date: June 9, 2016
    Applicant: Idibon, Inc.
    Inventors: Robert J. Munro, Rob Voigt, Schuyler D. Erle, Brendan D. Callahan, Gary C. King, Jessica D. Long, Jason Brenier, Tripti Saxena, Stefan Krawczyk
  • Patent number: 8676583
    Abstract: An action is performed in a spoken dialog system in response to a user's spoken utterance. A policy which maps belief states of user intent to actions is retrieved or created. A belief state is determined based on the spoken utterance, and an action is selected based on the determined belief state and the policy. The action is performed, and in one embodiment, involves requesting clarification of the spoken utterance from the user. Creating a policy may involve simulating user inputs and spoken dialog system interactions, and modifying policy parameters iteratively until a policy threshold is satisfied. In one embodiment, a belief state is determined by converting the spoken utterance into text, assigning the text to one or more dialog slots associated with nodes in a probabilistic ontology tree (POT), and determining a joint probability based on probability distribution tables in the POT and on the dialog slot assignments.
    Type: Grant
    Filed: August 30, 2011
    Date of Patent: March 18, 2014
    Assignee: Honda Motor Co., Ltd.
    Inventors: Rakesh Gupta, Deepak Ramachandran, Antoine Raux, Neville Mehta, Stefan Krawczyk, Matthew Hoffman
  • Publication number: 20120053945
    Abstract: An action is performed in a spoken dialog system in response to a user's spoken utterance. A policy which maps belief states of user intent to actions is retrieved or created. A belief state is determined based on the spoken utterance, and an action is selected based on the determined belief state and the policy. The action is performed, and in one embodiment, involves requesting clarification of the spoken utterance from the user. Creating a policy may involve simulating user inputs and spoken dialog system interactions, and modifying policy parameters iteratively until a policy threshold is satisfied. In one embodiment, a belief state is determined by converting the spoken utterance into text, assigning the text to one or more dialog slots associated with nodes in a probabilistic ontology tree (POT), and determining a joint probability based on probability distribution tables in the POT and on the dialog slot assignments.
    Type: Application
    Filed: August 30, 2011
    Publication date: March 1, 2012
    Applicant: HONDA MOTOR CO., LTD.
    Inventors: Rakesh Gupta, Deepak Ramachandran, Antoine Raux, Neville Mehta, Stefan Krawczyk, Matthew Hoffman