Patents by Inventor Sreeram Viswanath Balakrishnan
Sreeram Viswanath Balakrishnan 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: 20240119047Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: ApplicationFiled: October 16, 2023Publication date: April 11, 2024Inventors: Jayant Madhavan, Hongrae Lee, Sreeram Viswanath Balakrishnan, Warren H.Y. Shen
-
Patent number: 11789946Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: GrantFiled: February 14, 2022Date of Patent: October 17, 2023Assignee: GOOGLE LLCInventors: Jayant Madhavan, Hongrae Lee, Sreeram Viswanath Balakrishnan, Warren H. Y. Shen
-
Publication number: 20220171779Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: ApplicationFiled: February 14, 2022Publication date: June 2, 2022Inventors: Jayant Madhavan, Hongrae Lee, Sreeram Viswanath Balakrishnan, Warren H.Y. Shen
-
Patent number: 11249993Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: GrantFiled: May 22, 2020Date of Patent: February 15, 2022Assignee: GOOGLE LLCInventors: Jayant Madhavan, Hongrae Lee, Warren H. Y. Shen, Sreeram Viswanath Balakrishnan
-
Publication number: 20200293529Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: ApplicationFiled: May 22, 2020Publication date: September 17, 2020Inventors: Jayant Madhavan, Hongrae Lee, Warren H. Y. Shen, Sreeram Viswanath Balakrishnan
-
Patent number: 10698888Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: GrantFiled: January 26, 2018Date of Patent: June 30, 2020Assignee: Google LLCInventors: Jayant Madhavan, Hongrae Lee, Warren H. Y. Shen, Sreeram Viswanath Balakrishnan
-
Patent number: 10061757Abstract: Systems, methods, and computer-readable media are provided for searching a tabular database. According to certain embodiments, search parameters for searching a tabular database are received from a user device and a row of a tabular database that corresponds to the search parameters is determined. In certain embodiments, the row may be determined by comparing the search parameters with a plurality of stored exemplar search queries, each of the plurality of stored exemplar search queries comprising a search query associated with a row and a column of the tabular database. A column of the tabular database that corresponds to the search parameters is determined by comparing the search parameters with the plurality of stored exemplar search queries. In certain embodiments, at least one cell of the tabular database is determined. The determined cell may be located at the intersection of the determined row and the determined column.Type: GrantFiled: June 17, 2015Date of Patent: August 28, 2018Assignee: Google LLCInventors: Sreeram Viswanath Balakrishnan, Alon Yitzchak Halevy
-
Patent number: 9916348Abstract: In one aspect, a method includes receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query; identifying structured content set in a top-ranked subset of the resources, each structured content set being content arranged according to related attributes in one of the resources; for each identified structured content set, determining whether the query matches the structured content set based on terms of the query matching related attributes of the structured content set; selecting one of the structured content sets for which the query is determined to match; generating, from the selected structured content set, a structured fact set from the related attributes that matched the terms of the query; and providing the structured fact set with search results that identify the resources determined to be responsive to the query.Type: GrantFiled: August 12, 2015Date of Patent: March 13, 2018Assignee: Google LLCInventors: Jayant Madhavan, Hongrae Lee, Warren H. Y. Shen, Sreeram Viswanath Balakrishnan
-
Publication number: 20160140188Abstract: Systems, methods, and computer-readable media are provided for searching a tabular database. According to certain embodiments, search parameters for searching a tabular database are received from a user device and a row of a tabular database that corresponds to the search parameters is determined. In certain embodiments, the row may be determined by comparing the search parameters with a plurality of stored exemplar search queries, each of the plurality of stored exemplar search queries comprising a search query associated with a row and a column of the tabular database. A column of the tabular database that corresponds to the search parameters is determined by comparing the search parameters with the plurality of stored exemplar search queries. In certain embodiments, at least one cell of the tabular database is determined. The determined cell may be located at the intersection of the determined row and the determined column.Type: ApplicationFiled: June 17, 2015Publication date: May 19, 2016Inventors: Sreeram Viswanath Balakrishnan, Alon Yitzchak Halevy
-
Patent number: 8649552Abstract: A data obfuscation method, apparatus and computer program product are disclosed in which at least selected text entities such as words or abbreviations in a document are obfuscated to prevent the disclosure of private information if the document is disclosed. A user establishes various configuration parameters for selected text entities desired to obfuscated. The document is processed and text entities matching the configuration parameters are tagged for obfuscation. The tagged entities are then substituted in the document with obfuscating text. The obfuscating text can be derived from a hash table. The hash table may be used to provide a reverse obfuscation method by which original data can be restored to an obfuscated document.Type: GrantFiled: April 3, 2008Date of Patent: February 11, 2014Assignee: International Business Machines CorporationInventors: Sreeram Viswanath Balakrishnan, Rema Ananthanarayanan, Souptik Datta
-
Patent number: 7882099Abstract: A method (100) of crawling the Web (620) is disclosed. The method (100) crawls (120) Web pages on the Web starting from a given (110) set of seed Universal Resource Locators (URLs). Crawled Web pages are partitioned (140) into sets of relevant and irrelevant pages. A set of exclusion and/or inclusion patterns are discovered (150) from the sets of relevant and irrelevant pages, and subsequent crawling of the Web is restricted through the set of exclusion and/or inclusion patterns.Type: GrantFiled: March 25, 2008Date of Patent: February 1, 2011Assignee: International Business Machines CorporationInventors: Neeraj Agrawal, Sreeram Viswanath Balakrishnan, Sachindra Joshi
-
Patent number: 7724918Abstract: A data obfuscation method, apparatus and computer program product are disclosed in which at least selected text entities such as words or abbreviations in a document are obfuscated to prevent the disclosure of private information if the document is disclosed. A user establishes various configuration parameters for selected text entities desired to obfuscated. The document is processed and text entities matching the configuration parameters are tagged for obfuscation. The tagged entities are then substituted in the document with obfuscating text. The obfuscating text can be derived from a hash table. The hash table may be used to provide a reverse obfuscation method by which original data can be restored to an obfuscated document.Type: GrantFiled: November 22, 2006Date of Patent: May 25, 2010Assignee: International Business Machines CorporationInventors: Sreeram Viswanath Balakrishnan, Rema Ananthanarayanan, Souptik Datta
-
Publication number: 20080312921Abstract: In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.Type: ApplicationFiled: August 20, 2008Publication date: December 18, 2008Inventors: Scott E. Axelrod, Sreeram Viswanath Balakrishnan, Stanley F. Chen, Yuging Gao, Rameah A. Gopinath, Hong-Kwang Kuo, Benoit Maison, David Nahamoo, Michael Alan Picheny, George A. Saon, Geoffrey G. Zweig
-
Patent number: 7464031Abstract: In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.Type: GrantFiled: November 28, 2003Date of Patent: December 9, 2008Assignee: International Business Machines CorporationInventors: Scott E. Axelrod, Sreeram Viswanath Balakrishnan, Stanley F. Chen, Yuging Gao, Ramesh A. Gopinath, Hong-Kwang Kuo, Benoit Maison, David Nahamoo, Michael Alan Picheny, George A. Saon, Geoffrey G. Zweig
-
Publication number: 20080181396Abstract: A data obfuscation method, apparatus and computer program product are disclosed in which at least selected text entities such as words or abbreviations in a document are obfuscated to prevent the disclosure of private information if the document is disclosed. A user establishes various configuration parameters for selected text entities desired to obfuscated. The document is processed and text entities matching the configuration parameters are tagged for obfuscation. The tagged entities are then substituted in the document with obfuscating text. The obfuscating text can be derived from a hash table. The hash table may be used to provide a reverse obfuscation method by which original data can be restored to an obfuscated document.Type: ApplicationFiled: April 3, 2008Publication date: July 31, 2008Applicant: International Business Machines CorporationInventors: Sreeram Viswanath Balakrishnan, Rema Ananthanarayanan, Souptik Datta
-
Publication number: 20080168041Abstract: A method (100) of crawling the Web (620) is disclosed. The method (100) crawls (120) Web pages on the Web starting from a given (110) set of seed Universal Resource Locators (URLs). Crawled Web pages are partitioned (140) into sets of relevant and irrelevant pages. A set of exclusion and/or inclusion patterns are discovered (150) from the sets of relevant and irrelevant pages, and subsequent crawling of the Web is restricted through the set of exclusion and/or inclusion patterns.Type: ApplicationFiled: March 25, 2008Publication date: July 10, 2008Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Sachindra Joshi, Neeraj Agrawal, Sreeram Viswanath Balakrishnan
-
Patent number: 7379932Abstract: A method (100) of crawling the Web (620) is disclosed. The method (100) crawls (120) Web pages on the Web starting from a given (110) set of seed Universal Resource Locators (URLs). Crawled Web pages are partitioned (140) into sets of relevant and irrelevant pages. A set of exclusion and/or inclusion patterns are discovered (150) from the sets of relevant and irrelevant pages, and subsequent crawling of the Web is restricted through the set of exclusion and/or inclusion patterns.Type: GrantFiled: December 21, 2005Date of Patent: May 27, 2008Assignee: International Business Machines CorporationInventors: Neeraj Agrawal, Sreeram Viswanath Balakrishnan, Sachindra Joshi
-
Publication number: 20080118150Abstract: Data obfuscation of text data using entity detection and replacement A data obfuscation method, apparatus and computer program product are disclosed in which at least selected text entities such as words or abbreviations in a document are obfuscated to prevent the disclosure of private information if the document is disclosed. A user establishes various configuration parameters for selected text entities desired to obfuscated. The document is processed and text entities matching the configuration parameters are tagged for obfuscation. The tagged entities are then substituted in the document with obfuscating text. The obfuscating text can be derived from a hash table. The hash table may be used to provide a reverse obfuscation method by which original data can be restored to an obfuscated document.Type: ApplicationFiled: November 22, 2006Publication date: May 22, 2008Inventors: Sreeram Viswanath Balakrishnan, Rema Ananthanarayanan, Souptik Datta
-
Publication number: 20080086690Abstract: The present invention provides a hybrid call handling method and system. The method comprises navigating a plurality of received calls from a plurality of callers. The method further comprises monitoring a call health status for each of the plurality of the calls being navigated for entire call duration and notifying a bad call health status of the monitored call to a human agent for employing at least one rectification action. The call health status is determined by monitoring and measuring one or more call parameters. The invention provides for a system for call handling and navigation by an automated system with a human agent assisting the automated system for rectification of calls with bad call health status. Once the call with a bad health is transferred to the human agent, he assists the automated system either by directly communicating with the caller or by communicating using a machine interface.Type: ApplicationFiled: September 21, 2006Publication date: April 10, 2008Inventors: Ashish Verma, Nitendra Rajput, Sreeram Viswanath Balakrishnan, Tanveer Afzal Faruquie
-
Publication number: 20080072134Abstract: Token sequences within a number of documents are annotated. First, a base inverse index for unique tokens within the documents is received. The base inverse index includes a set of the unique tokens within the documents and a set of location lists for each unique token. Second, indices are created for a set of the token sequences within the documents from the base inverse index, to annotate the token sequences.Type: ApplicationFiled: September 19, 2006Publication date: March 20, 2008Inventors: Sreeram Viswanath Balakrishnan, Ganesh Ramakrishnan, Sachindra Joshi