Patents by Inventor Thorsten Brants
Thorsten Brants 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: 10885285Abstract: Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.Type: GrantFiled: August 29, 2018Date of Patent: January 5, 2021Assignee: Google LLCInventors: Franz Josef Och, Jeffrey Dean, Thorsten Brants, Alexander Mark Franz, Jay Ponte, Peng Xu, Sha-Mayn Teh, Jeffrey Chin, Ignacio E. Thayer, Anton Carver, Daniel Rosart, John S. Hawkins, Karel Driesen
-
Publication number: 20200410396Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.Type: ApplicationFiled: July 13, 2020Publication date: December 31, 2020Inventors: Zhifeng Chen, Michael Schuster, Melvin Jose Johnson Premkumar, Yonghui Wu, Quoc V. Le, Maxim Krikun, Thorsten Brants
-
Patent number: 10713593Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.Type: GrantFiled: December 29, 2016Date of Patent: July 14, 2020Assignee: Google LLCInventors: Zhifeng Chen, Michael Schuster, Melvin Jose Johnson Premkumar, Yonghui Wu, Quoc V. Le, Maxim Krikun, Thorsten Brants
-
Patent number: 10679148Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model. An exemplary system applying implicit bridging for machine learning tasks, as described in this specification, trains a machine learning model to perform certain types of machine learning tasks without requiring explicit training data for the certain types of machine learning tasks to be used during training.Type: GrantFiled: May 3, 2019Date of Patent: June 9, 2020Assignee: Google LLCInventors: Zhifeng Chen, Michael Schuster, Melvin Jose Johnson Premkumar, Yonghui Wu, Quoc V. Le, Maxim Krikun, Thorsten Brants
-
Publication number: 20190258961Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model. An exemplary system applying implicit bridging for machine learning tasks, as described in this specification, trains a machine learning model to perform certain types of machine learning tasks without requiring explicit training data for the certain types of machine learning tasks to be used during training.Type: ApplicationFiled: May 3, 2019Publication date: August 22, 2019Inventors: Zhifeng Chen, Michael Schuster, Melvin Jose Johnson Premkumar, Yonghui Wu, Quoc V. Le, Maxim Krikun, Thorsten Brants
-
Publication number: 20190018843Abstract: Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.Type: ApplicationFiled: August 29, 2018Publication date: January 17, 2019Inventors: Franz Josef Och, Jeffrey Dean, Thorsten Brants, Alexander Mark Franz, Jay Ponte, Peng Xu, Sha-Mayn Teh, Jeffrey Chin, Ignacio E. Thayer, Anton Carver, Daniel Rosart, John S. Hawkins, Karel Driesen
-
Patent number: 10089304Abstract: Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.Type: GrantFiled: April 6, 2017Date of Patent: October 2, 2018Assignee: Google LLCInventors: Franz Josef Och, Jeffrey Dean, Thorsten Brants, Alexander Mark Franz, Jay Ponte, Peng Xu, Sha-Mayn Teh, Jeffrey Chin, Ignacio E. Thayer, Anton Carver, Daniel Rosart, John S. Hawkins, Karel Driesen
-
Publication number: 20180129972Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.Type: ApplicationFiled: December 29, 2016Publication date: May 10, 2018Inventors: Zhifeng Chen, Michael Schuster, Melvin Jose Johnson Premkumar, Yonghui Wu, Quoc V. Le, Maxim Krikun, Thorsten Brants
-
Patent number: 9779139Abstract: A server is configured to receive, from a client, a query and context information associated with a document; obtain search results, based on the query, that identify documents relevant to the query; analyze the context information to identify content; generate first scores for a hierarchy of topics, that correspond to measures of relevance of the topics to the content; select a topic that is most relevant to the context information when the topic is associated with a greatest first score; generate second scores for the search results that correspond to measures of relevance, of the search results, to the topic; select one or more of the search results as being most relevant to the topic when the search results are associated with one or more greatest second scores; generate a search result document that includes the selected search results; and send, to a client, the search result document.Type: GrantFiled: March 15, 2016Date of Patent: October 3, 2017Assignee: Google Inc.Inventors: Sarveshwar Duddu, Kuntal Loya, Minh Tue Vo Thanh, Thorsten Brants
-
Publication number: 20170212887Abstract: Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.Type: ApplicationFiled: April 6, 2017Publication date: July 27, 2017Applicant: Google Inc.Inventors: Franz Josef Och, Jeffrey Dean, Thorsten Brants, Alexander Mark Franz, Jay Ponte, Peng Xu, Sha-Mayn Teh, Jeffrey Chin, Ignacio E. Thayer, Anton Carver, Daniel Rosart, John S. Hawkins, Karel Driesen
-
Patent number: 9619465Abstract: Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.Type: GrantFiled: May 23, 2014Date of Patent: April 11, 2017Assignee: GOOGLE INC.Inventors: Franz Josef Och, Jeffrey Dean, Thorsten Brants, Alexander Mark Franz, Jay Ponte, Peng Xu, Sha-Mayn Teh, Jeffrey Chin, Ignacio E. Thayer, Anton Carver, Daniel Rosart, John S. Hawkins, Karel Driesen
-
Patent number: 8972432Abstract: Systems, methods, and apparatuses, including computer program products, are provided for machine translation using information retrieval techniques. In general, in one implementation, a method is provided. The method includes providing a received input segment as a query to a search engine, the search engine searching an index of one or more collections of documents, receiving one or more candidate segments in response to the query, determining a similarity of each candidate segment to the received input segment, and for one or more candidate segments having a determined similarity that exceeds a threshold similarity, providing a translated target segment corresponding to the respective candidate segment.Type: GrantFiled: April 23, 2008Date of Patent: March 3, 2015Assignee: Google Inc.Inventors: Hayden Shaw, Thorsten Brants
-
Publication number: 20140257787Abstract: Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.Type: ApplicationFiled: May 23, 2014Publication date: September 11, 2014Applicant: GOOGLE INC.Inventors: Franz Josef Och, Jeffrey Dean, Thorsten Brants, Alexander Mark Franz, Jay Ponte, Peng Xu, Sha-Mayn Teh, Jeffrey Chin, Ignacio E. Thayer, Anton Carver, Daniel Rosart, John S. Hawkins, Karel Driesen
-
Patent number: 8812291Abstract: Systems, methods, and computer program products for machine translation are provided. In some implementations a system is provided. The system includes a language model including a collection of n-grams from a corpus, each n-gram having a corresponding relative frequency in the corpus and an order n corresponding to a number of tokens in the n-gram, each n-gram corresponding to a backoff n-gram having an order of n?1 and a collection of backoff scores, each backoff score associated with an n-gram, the backoff score determined as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.Type: GrantFiled: December 10, 2012Date of Patent: August 19, 2014Assignee: Google Inc.Inventors: Thorsten Brants, Ashok C. Popat, Peng Xu, Franz J. Och, Jeffrey Dean
-
Patent number: 8762128Abstract: A translation system receives a test pair that includes a source test phrase in a first language and a target test phrase in a second language. The test pair can be evaluated by comparing its components with phrases in primary pairs. The test source phrase can be compared to a primary source phrase that is the phrase most commonly translated by the machine translation system into the test target phrase. The test target phrase can be compared to a primary target phrase that is the phrase into which the target source phrase is most often translated. If one and/or both comparisons are sufficiently dissimilar, the machine translation system can be modified by deleting the test pair, by flagging it for human review, or in other ways.Type: GrantFiled: May 31, 2011Date of Patent: June 24, 2014Assignee: Google Inc.Inventors: Thorsten Brants, Jan Pfeifer
-
Patent number: 8762368Abstract: A server is configured to receive, from a client, a query and context information associated with a document; obtain search results, based on the query, that identify documents relevant to the query; analyze the context information to identify content; generate first scores for a hierarchy of topics, that correspond to measures of relevance of the topics to the content; select a topic that is most relevant to the context information when the topic is associated with a greatest first score; generate second scores for the search results that correspond to measures of relevance, of the search results, to the topic; select one or more of the search results as being most relevant to the topic when the search results are associated with one or more greatest second scores; generate a search result document that includes the selected search results; and send, to a client, the search result document.Type: GrantFiled: April 30, 2012Date of Patent: June 24, 2014Assignee: Google Inc.Inventors: Sarveshwar Duddu, Kuntal Loya, Minh Tue Vo Thanh, Thorsten Brants
-
Patent number: 8738357Abstract: Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.Type: GrantFiled: October 22, 2012Date of Patent: May 27, 2014Assignee: Google Inc.Inventors: Franz Josef Och, Jeffrey Dean, Thorsten Brants, Alexander Mark Franz, Jay Ponte, Peng Xu, Sha-Mayn Teh, Jeffrey Chin, Ignacio E. Thayer, Anton Carver, Daniel Rosart, John S. Hawkins, Karel Driesen
-
Publication number: 20140059033Abstract: Systems, methods, and apparatuses, including computer program products, are provided for machine translation using information retrieval techniques. In general, in one implementation, a method is provided. The method includes providing a received input segment as a query to a search engine, the search engine searching an index of one or more collections of documents, receiving one or more candidate segments in response to the query, determining a similarity of each candidate segment to the received input segment, and for one or more candidate segments having a determined similarity that exceeds a threshold similarity, providing a translated target segment corresponding to the respective candidate segment.Type: ApplicationFiled: April 23, 2008Publication date: February 27, 2014Applicant: Google Inc.Inventors: Hayden Shaw, Thorsten Brants
-
Patent number: 8626492Abstract: A semantic locator determines whether input sequences form semantically meaningful units. The semantic locator includes a coherence component that calculates a coherence of the terms in the sequence and a variation component that calculates the variation in terms that surround the sequence. A heuristics component may additionally refine results of the coherence component and the variation component. A decision component may make the determination of whether the sequence is a semantic unit based on the results of the coherence component, variation component, and heuristics component.Type: GrantFiled: January 11, 2013Date of Patent: January 7, 2014Assignee: Google Inc.Inventors: Thorsten Brants, Jay Ponte
-
Patent number: 8554769Abstract: This specification describes technologies relating to providing search results. One aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving a network resource, the network resource including text content; generating a language model score for the resource including applying a language model to the text content of the resource; generating a query stuffing score for the reference, the query stuffing score being a function of term frequency in the resource content and a query index; calculating a gibberish score for the resource using the language model score and the query stuffing score; and using the calculated gibberish score to determine whether to modify a ranking score of the resource.Type: GrantFiled: June 17, 2009Date of Patent: October 8, 2013Assignee: Google Inc.Inventors: Shashidhar A. Thakur, Sushrut Karanjkar, Pavel Levin, Thorsten Brants