Patents by Inventor Alexandre Rochette

Alexandre Rochette 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: 20220230089
    Abstract: A classifier may be trained with less than all datasets manually annotated with labels. A small subset of verbatims may be manually labeled with topic labels as seeds. Data augmentations can be used to acquire seed verbatim sets for known topics and to assign temporary pseudo labels to the rest of the verbatims based on their vector space proximity to the labeled seed verbatims. The training may involve classification epochs during which embeddings are updated with the assumption that the pseudo labels are ground-truth labels. The training may also involve labeling epochs during which the updated embeddings are used to update the vectors corresponding to the verbatims, and pseudo labels are updated based on updated vector coordinates in the vector space. As the training process progresses through the epochs, the embeddings will converge.
    Type: Application
    Filed: January 15, 2021
    Publication date: July 21, 2022
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Soyoung PERAUD, Alexandre ROCHETTE, Gabriel Arien DESGARENNES, Niel CHAH, Abhishek KUMAR, Timothy James HAZEN
  • Publication number: 20220100972
    Abstract: Examples of the present disclosure describe systems and methods of configuring generic language understanding models. In aspects, one or more previously configured schemas for various applications may be identified and collected. A generic schema may be generated using the collected schemas. The collected schemas may be programmatically mapped to the generic schema. The generic schema may be used to train on ore more models. An interface may be provided to allow browsing the models. The interface may include a configuration mechanism that provides for selecting on or more of the models. The selected models may be bundled programmatically, such that the information and instructions needed to implement the models are configured programmatically. The bundled models may then be provided to a requestor.
    Type: Application
    Filed: December 14, 2021
    Publication date: March 31, 2022
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Ruhi Sarikaya, Asli Celikyilmaz, Young-Bum Kim, Zhaleh Feizollahi, Nikhil Ramesh, Hisami Suzuki, Alexandre Rochette
  • Patent number: 11061550
    Abstract: Aspects herein provide third party application authors with a user interface authoring platform that automates and simplifies a task definition process while also providing the ability to leverage pre-existing language understanding models and canonicalization and resolution modules that are provided by the operating system on which the CU system resides or as provided by other third parties. In particular, the present disclosure provides a method and system for authoring a task using a user interface authoring platform.
    Type: Grant
    Filed: March 26, 2020
    Date of Patent: July 13, 2021
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Marius Alexandru Marin, Paul Anthony Crook, Nikhil Holenarsipur Ramesh, Vipul Agarwal, Omar Zia Khan, Alexandre Rochette, Jean-Philippe Robichaud, Ruhi Sarikaya
  • Patent number: 10909325
    Abstract: Multi-turn cross-domain natural language understanding (NLU) systems and platforms for building the multi-turn cross-domain NLU system are provided. Further, methods for using and building the multi-turn cross-domain NLU system are provided. More specifically, the multi-turn cross-domain NLU system supports multi-turn bot/agent/application scenarios for new domains without having to select a task definition and/or define a new schema during the building of the NLU system. Accordingly, the platform for building the multi-turn cross-domain NLU system that does not require the builder to select a task and/or build a schema for a selected task provides an easy to use, cost effective, and efficient service for building a NLU system. Further, the multi-turn cross-domain NLU system provides a more versatile NLU system than previously utilized NLU systems that were trained for and limited to a selected task and/or domain.
    Type: Grant
    Filed: June 12, 2019
    Date of Patent: February 2, 2021
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ruhi Sarikaya, Young-Bum Kim, Alexandre Rochette
  • Publication number: 20200226216
    Abstract: This document relates to compression of information into a human-readable format, such as a sentence or phrase. Generally, the disclosed techniques can extract values, such as purposes and topics, from information items and generate compressed representations of the information items that include the extracted values. In some cases, machine learning models can be employed to extract the values, and also to rank the values for inclusion in the compressed representations.
    Type: Application
    Filed: January 10, 2019
    Publication date: July 16, 2020
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Marius A. MARIN, Alexandre ROCHETTE, Daniel BOIES, Vashutosh AGRAWAL, Bodin DRESEVIC
  • Publication number: 20200225839
    Abstract: Aspects herein provide third party application authors with a user interface authoring platform that automates and simplifies a task definition process while also providing the ability to leverage pre-existing language understanding models and canonicalization and resolution modules that are provided by the operating system on which the CU system resides or as provided by other third parties. In particular, the present disclosure provides a method and system for authoring a task using a user interface authoring platform.
    Type: Application
    Filed: March 26, 2020
    Publication date: July 16, 2020
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Marius Alexandru Marin, Paul Anthony Crook, Nikhil Holenarsipur Ramesh, Vipul Agarwal, Omar Zia Khan, Alexandre Rochette, Jean-Philippe Robichaud, Ruhi Sarikaya
  • Patent number: 10643035
    Abstract: A computer-implemented technique is described for facilitating the creation of a language understanding (LU) component for use with an application. The technique allows a developer to select a subset of parameters from a larger set of parameters. The subset of parameters pertains to a LU scenario to be handled by the application. The larger set of parameters pertains to a plurality of LU scenarios handled by an already-existing generic LU model. The technique creates a constrained LU component that is based on the subset of parameters in conjunction with the generic LU model. At runtime, the constrained LU component interprets input language items using the generic LU model in a manner that is constrained by the subset of parameters that have been selected, to provide an output result. The technique also allows the developer to create new rules and/or supplemental models.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: May 5, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Young-Bum Kim, Ruhi Sarikaya, Alexandre Rochette
  • Publication number: 20200135201
    Abstract: Conversational understanding systems allow users to conversationally interface with a computing device. In examples, a query may be received that includes a request for execution of a task. A data exchange task definition may be accessed. The data exchange task definition assists a conversational understanding system in managing task state tracking for information needed for task execution. Using the data exchange task definition, a per-turn policy for interacting with the user computing device is generated based on the state of a dialogue with a computing device and an evaluation of a process flow chart provided by a task owner resource. The task owner resource may be independent from the conversational understanding system. A response to the query may be generated and output based on the per-turn policy. In examples, the per-turn policy is used to generate one or more responses during a dialogue with a user via a computing device.
    Type: Application
    Filed: December 20, 2019
    Publication date: April 30, 2020
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Paul CROOK, Vasiliy RADOSTEV, Omar Zia KHAN, Vipul AGARWAL, Ruhi SARIKAYA, Marius Alexandru MARIN, Alexandre ROCHETTE, Jean-Philippe ROBICHAUD
  • Patent number: 10635281
    Abstract: Aspects herein provide third party application authors with a user interface authoring platform that automates and simplifies a task definition process while also providing the ability to leverage pre-existing language understanding models and canonicalization and resolution modules that are provided by the operating system on which the CU system resides or as provided by other third parties. In particular, the present disclosure provides a method and system for authoring a task using a user interface authoring platform.
    Type: Grant
    Filed: February 12, 2016
    Date of Patent: April 28, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Marius Alexandru Marin, Paul Anthony Crook, Nikhil Holenarsipur Ramesh, Vipul Agarwal, Omar Zia Khan, Alexandre Rochette, Jean-Philippe Robichaud, Ruhi Sarikaya
  • Publication number: 20190318000
    Abstract: A computer-implemented technique is described for facilitating the creation of a language understanding (LU) component for use with an application. The technique allows a developer to select a subset of parameters from a larger set of parameters. The subset of parameters pertains to a LU scenario to be handled by the application. The larger set of parameters pertains to a plurality of LU scenarios handled by an already-existing generic LU model. The technique creates a constrained LU component that is based on the subset of parameters in conjunction with the generic LU model. At runtime, the constrained LU component interprets input language items using the generic LU model in a manner that is constrained by the subset of parameters that have been selected, to provide an output result. The technique also allows the developer to create new rules and/or supplemental models.
    Type: Application
    Filed: June 25, 2019
    Publication date: October 17, 2019
    Inventors: Young-Bum Kim, Ruhi Sarikaya, Alexandre Rochette
  • Publication number: 20190294680
    Abstract: Multi-turn cross-domain natural language understanding (NLU) systems and platforms for building the multi-turn cross-domain NLU system are provided. Further, methods for using and building the multi-turn cross-domain NLU system are provided. More specifically, the multi-turn cross-domain NLU system supports multi-turn bot/agent/application scenarios for new domains without having to select a task definition and/or define a new schema during the building of the NLU system. Accordingly, the platform for building the multi-turn cross-domain NLU system that does not require the builder to select a task and/or build a schema for a selected task provides an easy to use, cost effective, and efficient service for building a NLU system. Further, the multi-turn cross-domain NLU system provides a more versatile NLU system than previously utilized NLU systems that were trained for and limited to a selected task and/or domain.
    Type: Application
    Filed: June 12, 2019
    Publication date: September 26, 2019
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Ruhi SARIKAYA, Young-Bum KIM, Alexandre ROCHETTE
  • Patent number: 10417346
    Abstract: A computer-implemented technique is described for facilitating the creation of a language understanding (LU) component for use with an application. The technique allows a developer to select a subset of parameters from a larger set of parameters. The subset of parameters pertains to a LU scenario to be handled by the application. The larger set of parameters pertains to a plurality of LU scenarios handled by an already-existing generic LU model. The technique creates a constrained LU component that is based on the subset of parameters in conjunction with the generic LU model. At runtime, the constrained LU component interprets input language items using the generic LU model in a manner that is constrained by the subset of parameters that have been selected, to provide an output result. The technique also allows the developer to create new rules and/or supplemental models.
    Type: Grant
    Filed: January 23, 2016
    Date of Patent: September 17, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Young-Bum Kim, Ruhi Sarikaya, Alexandre Rochette
  • Patent number: 10360300
    Abstract: Multi-turn cross-domain natural language understanding (NLU) systems and platforms for building the multi-turn cross-domain NLU system are provided. Further, methods for using and building the multi-turn cross-domain NLU system are provided. More specifically, the multi-turn cross-domain NLU system supports multi-turn bot/agent/application scenarios for new domains without having to select a task definition and/or define a new schema during the building of the NLU system. Accordingly, the platform for building the multi-turn cross-domain NLU system that does not require the builder to select a task and/or build a schema for a selected task provides an easy to use, cost effective, and efficient service for building a NLU system. Further, the multi-turn cross-domain NLU system provides a more versatile NLU system than previously utilized NLU systems that were trained for and limited to a selected task and/or domain.
    Type: Grant
    Filed: August 24, 2016
    Date of Patent: July 23, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ruhi Sarikaya, Young-Bum Kim, Alexandre Rochette
  • Patent number: 10007660
    Abstract: Methods and systems are provided for contextual language understanding. A natural language expression may be received at a single-turn model and a multi-turn model for determining an intent of a user. For example, the single-turn model may determine a first prediction of at least one of a domain classification, intent classification, and slot type of the natural language expression. The multi-turn model may determine a second prediction of at least one of a domain classification, intent classification, and slot type of the natural language expression. The first prediction and the second prediction may be combined to produce a final prediction relative to the intent of the natural language expression. An action may be performed based on the final prediction of the natural language expression.
    Type: Grant
    Filed: May 26, 2017
    Date of Patent: June 26, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ruhi Sarikaya, Puyang Xu, Alexandre Rochette, Asli Celikyilmaz
  • Patent number: 9996532
    Abstract: Systems and methods for building a dialog-state specific multi-turn contextual language understanding system are provided. More specifically, the systems and methods infer or are configured to infer a state-specific schema and/or state-specific rules from a formed single-shot language understanding model and/or a single-shot rule set. As such, the systems and methods only require the information necessary to form a single-shot language understanding model and/or a single-shot rule set from a builder to form or build the dialog-state specific multi-turn contextual language understanding system.
    Type: Grant
    Filed: June 17, 2016
    Date of Patent: June 12, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ruhi Sarikaya, Young-Bum Kim, Alexandre Rochette
  • Patent number: 9978361
    Abstract: Systems and methods for building a dialog-state specific multi-turn contextual language understanding system are provided. More specifically, the systems and methods infer or are configured to infer a state-specific schema and/or state-specific rules from a formed single-shot language understanding model and/or a single-shot rule set. As such, the systems and methods only require the information necessary to form a single-shot language understanding model and/or a single-shot rule set from a builder to form or build the dialog-state specific multi-turn contextual language understanding system.
    Type: Grant
    Filed: June 20, 2016
    Date of Patent: May 22, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ruhi Sarikaya, Young-Bum Kim, Alexandre Rochette
  • Publication number: 20180060303
    Abstract: Multi-turn cross-domain natural language understanding (NLU) systems and platforms for building the multi-turn cross-domain NLU system are provided. Further, methods for using and building the multi-turn cross-domain NLU system are provided. More specifically, the multi-turn cross-domain NLU system supports multi-turn bot/agent/application scenarios for new domains without having to select a task definition and/or define a new schema during the building of the NLU system. Accordingly, the platform for building the multi-turn cross-domain NLU system that does not require the builder to select a task and/or build a schema for a selected task provides an easy to use, cost effective, and efficient service for building a NLU system. Further, the multi-turn cross-domain NLU system provides a more versatile NLU system than previously utilized NLU systems that were trained for and limited to a selected task and/or domain.
    Type: Application
    Filed: August 24, 2016
    Publication date: March 1, 2018
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Ruhi Sarikaya, Young-Bum Kim, Alexandre Rochette
  • Patent number: 9892208
    Abstract: User input expressed as text may be analyzed for determining a type of response, such as an application response, and/or determining a type of task that is requested by the user input. Entity representations may be identified, classified and/or or tagged based on a type of response, type of task and/or a set of entity types. A surface form of an entity, ambiguous entity representation and/or other type of expression within the user input may be resolved, normalized and/or mapped to a normalized value. Normalizing entities and/or entity attributes may involve using a set of normalization rules, a lookup table, one or more machined learned methods, and/or an entity normalization index that associates entities with alternate surface forms derived from web corpora. The normalized value may be used to construct a request to a structured knowledge source and/or an application.
    Type: Grant
    Filed: April 2, 2014
    Date of Patent: February 13, 2018
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Tasos Anastasakos, Alexandre Rochette, Ruhi Sarikaya
  • Publication number: 20180005629
    Abstract: Conversational understanding systems allow users to conversationally interface with a computing device. In examples, a query may be received that includes a request for execution of a task. A data exchange task definition may be accessed. The data exchange task definition assists a conversational understanding system in managing task state tracking for information needed for task execution. Using the data exchange task definition, a per-turn policy for interacting with the user computing device is generated based on the state of a dialogue with a computing device and an evaluation of a process flow chart provided by a task owner resource. The task owner resource may be independent from the conversational understanding system. A response to the query may be generated and output based on the per-turn policy. In examples, the per-turn policy is used to generate one or more responses during a dialogue with a user via a computing device.
    Type: Application
    Filed: June 30, 2016
    Publication date: January 4, 2018
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Paul Crook, Vasiliy Radostev, Omar Zia Khan, Vipul Agarwal, Ruhi Sarikaya, Marius Alexandru Marin, Alexandre Rochette, Jean-Philippe Robichaud
  • Publication number: 20170364505
    Abstract: Systems and methods for building a dialog-state specific multi-turn contextual language understanding system are provided. More specifically, the systems and methods infer or are configured to infer a state-specific schema and/or state-specific rules from a formed single-shot language understanding model and/or a single-shot rule set. As such, the systems and methods only require the information necessary to form a single-shot language understanding model and/or a single-shot rule set from a builder to form or build the dialog-state specific multi-turn contextual language understanding system.
    Type: Application
    Filed: June 17, 2016
    Publication date: December 21, 2017
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Ruhi Sarikaya, Young-Bum Kim, Alexandre Rochette