Patents by Inventor John Blitzer
John Blitzer 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: 11900068Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.Type: GrantFiled: August 9, 2023Date of Patent: February 13, 2024Assignee: GOOGLE LLCInventors: Matthew K. Gray, John Blitzer, Corinn Herrick, Srinivasan Venkatachary, Jayant Madhavan, Sam Oates, Phiroze Parakh, Aditya Shah, Mahsan Rofouei, Ibrahim Badr
-
Patent number: 11886828Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.Type: GrantFiled: August 22, 2023Date of Patent: January 30, 2024Assignee: GOOGLE LLCInventors: Matthew K. Gray, John Blitzer, Corinn Herrick, Srinivasan Venkatachary, Jayant Madhavan, Sam Oates, Phiroze Parakh, Aditya Shah, Mahsan Rofouei, Ibrahim Badr
-
Publication number: 20230342411Abstract: Techniques of generating short answers for queries by a search engine include performing a training operation on a corpus of training data to train the score prediction engine, the corpus of training data including candidate passages providing short answers for display in callouts and remaining respective passages, from which a top scoring short answer is generated. In such implementations, the corpus of training data further includes the remaining respective passages and the respective titles of the candidate passage and remaining respective passages.Type: ApplicationFiled: March 9, 2022Publication date: October 26, 2023Inventors: Preyas Dalsukhbhai Popat, Gaurav Bhaskar Gite, John Blitzer, Jayant Madhavan, Aliaksei Severyn
-
Patent number: 11769017Abstract: At least selectively utilizing a large language model (LLM) in generating a natural language (NL) based summary to be rendered in response to a query. In some implementations, in generating the NL based summary additional content is processed using the LLM. The additional content is in addition to query content of the query itself and, in generating the NL based summary, can be processed using the LLM and along with the query content—or even independent of the query content. Processing the additional content can, for example, mitigate occurrences of the NL based summary including inaccuracies and/or can mitigate occurrences of the NL based summary being over-specified and/or under-specified.Type: GrantFiled: March 20, 2023Date of Patent: September 26, 2023Assignee: GOOGLE LLCInventors: Matthew K. Gray, John Blitzer, Corinn Herrick, Srinivasan Venkatachary, Jayant Madhavan, Sam Oates, Phiroze Parakh, Aditya Shah, Mahsan Rofouei, Ibrahim Badr
-
Patent number: 11403288Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.Type: GrantFiled: October 13, 2020Date of Patent: August 2, 2022Assignee: GOOGLE LLCInventors: Amarnag Subramanya, Fernando Pereira, Ni Lao, John Blitzer, Rahul Gupta
-
Publication number: 20210026846Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.Type: ApplicationFiled: October 13, 2020Publication date: January 28, 2021Inventors: Amarnag Subramanya, Fernando Pereira, Ni Lao, John Blitzer, Rahul Gupta
-
Patent number: 10846293Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a statement that references a particular attribute of a particular topic, in response to providing the statement, obtaining one or more query patterns that each include one or more query terms that are used in queries submitted to a search system in obtaining a value for the particular attribute of the particular topic, generalizing one or more of the query patterns, and associating the one or more generalized query patterns with one or more other topics that include the particular attribute.Type: GrantFiled: January 16, 2018Date of Patent: November 24, 2020Assignee: Google LLCInventors: Junli Xian, Engin Cinar Sahin, John Blitzer, Emma S. Persky
-
Patent number: 10810193Abstract: Implementations include systems and methods for querying a data graph. An example method includes receiving a machine learning module trained to produce a model with multiple features for a query, each feature representing a path in a data graph. The method also includes receiving a search query that includes a first search term, mapping the search query to the query, and mapping the first search term to a first entity in the data graph. The method may also include identifying a second entity in the data graph using the first entity and at least one of the multiple weighted features, and providing information relating to the second entity in a response to the search query. Some implementations may also include training the machine learning module by, for example, generating positive and negative training examples from an answer to a query.Type: GrantFiled: March 13, 2013Date of Patent: October 20, 2020Assignee: GOOGLE LLCInventors: Amarnag Subramanya, Fernando Pereira, Ni Lao, John Blitzer, Rahul Gupta
-
Patent number: 10521479Abstract: The present disclosure relates to evaluating different semantic interpretations of a search query. One example method includes obtaining a set of search results for a particular search query submitted to a search engine; obtaining a set of semantic interpretations for the particular search query; obtaining, for each semantic interpretation of the set, a canonical search query; generating a modified search query based at least in part on the particular search query and the canonical search query for the semantic interpretation; obtaining a set of search results for the modified search query for the semantic interpretation; and determining, for each semantic interpretation of the set, a degree of similarity between (i) the set of search results of the modified search query for the semantic interpretation, and (ii) the set of search results for the particular search query.Type: GrantFiled: May 20, 2019Date of Patent: December 31, 2019Assignee: Google LLCInventors: Ashish Venugopal, Jakob D. Uszkoreit, John Blitzer, Edward Everett Anderson
-
Publication number: 20190278813Abstract: The present disclosure relates to evaluating different semantic interpretations of a search query. One example method includes obtaining a set of search results for a particular search query submitted to a search engine; obtaining a set of semantic interpretations for the particular search query; obtaining, for each semantic interpretation of the set, a canonical search query; generating a modified search query based at least in part on the particular search query and the canonical search query for the semantic interpretation; obtaining a set of search results for the modified search query for the semantic interpretation; and determining, for each semantic interpretation of the set, a degree of similarity between (i) the set of search results of the modified search query for the semantic interpretation, and (ii) the set of search results for the particular search query.Type: ApplicationFiled: May 20, 2019Publication date: September 12, 2019Inventors: Ashish Venugopal, Jakob D. Uszkoreit, John Blitzer, Edward Everett Anderson
-
Patent number: 10353964Abstract: The present disclosure relates to evaluating different semantic interpretations of a search query. One example method includes obtaining a set of search results for a particular search query submitted to a search engine; obtaining a set of semantic interpretations for the particular search query; obtaining, for each semantic interpretation of the set, a canonical search query; generating a modified search query based at least in part on the particular search query and the canonical search query for the semantic interpretation; obtaining a set of search results for the modified search query for the semantic interpretation; and determining, for each semantic interpretation of the set, a degree of similarity between (i) the set of search results of the modified search query for the semantic interpretation, and (ii) the set of search results for the particular search query.Type: GrantFiled: March 11, 2015Date of Patent: July 16, 2019Assignee: Google LLCInventors: Ashish Venugopal, Jakob D. Uszkoreit, John Blitzer, Edward Everett Anderson
-
Publication number: 20190130251Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a system output from a system input using a neural network system comprising an encoder neural network configured to, for each of a plurality of encoder time steps, receive an input sequence comprising a respective question token, and process the question token at the encoder time step to generate an encoded representation of the question token, and a decoder neural network configured to, for each of a plurality of decoder time steps, receive a decoder input, and process the decoder input and a preceding decoder hidden state to generate an updated decoder hidden state.Type: ApplicationFiled: October 31, 2018Publication date: May 2, 2019Inventors: Ni Lao, Chen Liang, Quoc V. Le, John Blitzer
-
Patent number: 10108700Abstract: Methods and systems are provided for a question answering. In some implementations, a data element to be updated is identified in a knowledge graph and a query is generated based at least in part on the data element. The query is provided to a query processing engine. Information is received from the query processing engine in response to the query. The knowledge graph is updated based at least in part on the received information.Type: GrantFiled: March 15, 2013Date of Patent: October 23, 2018Assignee: GOOGLE LLCInventors: Rahul Gupta, Shaohua Sun, John Blitzer, Dekang Lin, Evgeniy Gabrilovich
-
Patent number: 9984684Abstract: A language processing system collects similar queries and respective responses and aggregated by responses. Incorrect responses are determined and filtered by the aggregation. The remaining responses are then used to query a high precision system for attributes of entities specified by the queries. The attribute type is determined from the responses of the high precision system, and corresponding parse rules are generated. The parse rules are then associated with an operation that yields a response that specifies an attribute of the attribute type.Type: GrantFiled: June 25, 2013Date of Patent: May 29, 2018Assignee: Google LLCInventors: Jakob D. Uszkoreit, John Blitzer, Engin Cinar Sahin, Rahul Gupta, Dekang Lin, Fernando Pereira
-
Patent number: 9898512Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a statement that references a particular attribute of a particular topic, in response to providing the statement, obtaining one or more query patterns that each include one or more query terms that are used in queries submitted to a search system in obtaining a value for the particular attribute of the particular topic, generalizing one or more of the query patterns, and associating the one or more generalized query patterns with one or more other topics that include the particular attribute.Type: GrantFiled: May 13, 2015Date of Patent: February 20, 2018Assignee: Google Inc.Inventors: Junli Xian, Engin Cinar Sahin, John Blitzer, Emma S. Persky
-
Patent number: 9405849Abstract: A method identifies pairs of first and second command inputs from respective user device sessions for which the first and second operation data are indicative of a first operation failure and a second operation success. The first operation data indicate a first operation performed on data from a first resource property in response to the first command input, and the second operation data indicate a second operation performed on data from a second resource property in response to the second command input. They system determines, from the identified pairs of first and second command inputs, command inputs for which a parsing rule that is associated with the second operation is to be generated.Type: GrantFiled: March 29, 2016Date of Patent: August 2, 2016Assignee: Google Inc.Inventors: Jakob D. Uszkoreit, John Blitzer, Engin Cinar Sahin, Rahul Gupta, Dekang Lin, Fernando Pereira, Ciprian I. Chelba
-
Patent number: 9330195Abstract: A method identifies pairs of first and second command inputs from respective user device sessions for which the first and second operation data are indicative of a first operation failure and a second operation success. The first operation data indicate a first operation performed on data from a first resource property in response to the first command input, and the second operation data indicate a second operation performed on data from a second resource property in response to the second command input. They system determines, from the identified pairs of first and second command inputs, command inputs for which a parsing rule that is associated with the second operation is to be generated.Type: GrantFiled: June 25, 2013Date of Patent: May 3, 2016Assignee: Google Inc.Inventors: Jakob D. Uszkoreit, John Blitzer, Engin Cinar Sahin, Rahul Gupta, Dekang Lin, Fernando Pereira, Ciprian I. Chelba
-
Publication number: 20160078131Abstract: The present disclosure relates to evaluating different semantic interpretations of a search query. One example method includes obtaining a set of search results for a particular search query submitted to a search engine; obtaining a set of semantic interpretations for the particular search query; obtaining, for each semantic interpretation of the set, a canonical search query; generating a modified search query based at least in part on the particular search query and the canonical search query for the semantic interpretation; obtaining a set of search results for the modified search query for the semantic interpretation; and determining, for each semantic interpretation of the set, a degree of similarity between (i) the set of search results of the modified search query for the semantic interpretation, and (ii) the set of search results for the particular search query.Type: ApplicationFiled: March 11, 2015Publication date: March 17, 2016Inventors: Ashish Venugopal, Jakob D. Uszkoreit, John Blitzer, Edward Everett Anderson
-
Publication number: 20150205866Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for retrieving documents. One of the methods includes receiving a search query that includes a first query term and an adjacent, second query term, and a substitute term for the first query term. A determination is made that the first query term and the substitute term satisfy one or more predetermined criteria and that a resource does not include the first query term. The resource is selected to be scored only if the substitute term occurs adjacent to the second term in the resource.Type: ApplicationFiled: May 31, 2012Publication date: July 23, 2015Applicant: GOOGLE INC.Inventors: Hayden Shaw, Robert B. Avery, Trystan G. Upstill, Thomas Strohmann, Pi-Chuan Chang, John Blitzer, P. Pandurang Nayak
-
Patent number: 9037568Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a statement that references a particular attribute of a particular topic, in response to providing the statement, obtaining one or more query patterns that each include one or more query terms that are used in queries submitted to a search system in obtaining a value for the particular attribute of the particular topic, generalizing one or more of the query patterns, and associating the one or more generalized query patterns with one or more other topics that include the particular attribute.Type: GrantFiled: March 15, 2013Date of Patent: May 19, 2015Assignee: Google Inc.Inventors: Junli Xian, Engin Cinar Sahin, John Blitzer, Emma S. Persky