Patents by Inventor Arul Menezes

Arul Menezes 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: 8082143
    Abstract: In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
    Type: Grant
    Filed: July 8, 2009
    Date of Patent: December 20, 2011
    Assignee: Microsoft Corporation
    Inventors: Arul A. Menezes, Christopher B. Quirk, Colin A. Cherry
  • Patent number: 8065307
    Abstract: The present invention may be used to analyze subject content, search and analyze reference content, compare the subject and reference content for similarity, and output comparison reports between the subject and reference content. The present invention may incorporate and utilize text from intrinsic and/or extrinsic subject documents. The analysis may employ a variety of metrics, including scores generated from a natural language processing system, scores based on classification similarity, scores based on proximity similarity, and in the case of analysis of patent documents, scores based on measurement of claims.
    Type: Grant
    Filed: December 20, 2006
    Date of Patent: November 22, 2011
    Assignee: Microsoft Corporation
    Inventors: Brian Dean Haslam, Patrick Wayne John Evans, Arul Menezes, Patrick Santos
  • Publication number: 20100223049
    Abstract: A computer-implemented machine translation system translates text from a first language to a second language. The system includes a plurality of mappings, each mapping indicative of associating a dependency structure of the first language with a dependency structure of the second language, wherein at least some of the mappings correspond to dependency structures of the first language having varying context with some common elements, and associated dependency structures of the second language to the dependency structures of the first language. A module receives input text in a first language and outputs output text in a second language based on accessing the plurality of mappings.
    Type: Application
    Filed: May 4, 2010
    Publication date: September 2, 2010
    Applicant: Microsoft Corporation
    Inventors: Arul A. Menezes, Stephen D. Richardson
  • Patent number: 7734459
    Abstract: A method of aligning nodes of dependency structures obtained from a bilingual corpus includes a two-phase approach wherein a first phase comprises associating nodes of the dependency structures to form tentative correspondences. The nodes of the dependency structures are then aligned as a function of the tentative correspondences and structural considerations. Mappings are obtained from the aligned dependency structures. The mappings can be expanded with varying types and amounts of local context in order that a more fluent translation can be obtained when translation is performed.
    Type: Grant
    Filed: July 5, 2001
    Date of Patent: June 8, 2010
    Assignee: Microsoft Corporation
    Inventors: Arul A. Menezes, Stephen D. Richardson
  • Patent number: 7698124
    Abstract: In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
    Type: Grant
    Filed: December 16, 2004
    Date of Patent: April 13, 2010
    Assignee: Microsoft Corporaiton
    Inventors: Arul A. Menezes, Christopher B. Quirk, Colin A. Cherry
  • Publication number: 20090326911
    Abstract: Many machine translation scenarios involve the generation of a language translation rule set based on parallel training corpuses (e.g., sentences in a first language and word-for-word translations into a second language.) However, the translation of a source corpus in a source language to a target corpus in a target language involves at least two aspects: selecting elements of the target language to match the elements of the source corpus, and ordering the target elements according to the semantic organization of the source corpus and the grammatic rules of the target language. The breadth of generalization of the translation rules derived from the training may be improved, while retaining contextual information, by formulating language order templates that specify orderings of small sets of target elements according to target element types.
    Type: Application
    Filed: June 26, 2008
    Publication date: December 31, 2009
    Applicant: MICROSOFT CORPORATION
    Inventors: Arul A. Menezes, Christopher B. Quirk
  • Publication number: 20090271177
    Abstract: In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
    Type: Application
    Filed: July 8, 2009
    Publication date: October 29, 2009
    Applicant: Microsoft Corporation
    Inventors: Arul A. Menezes, Christopher B. Quirk, Colin A. Cherry
  • Patent number: 7593843
    Abstract: A method of decoding an input semantic structure to generate an output semantic structure. A set of transfer mappings are provided. A score is calculated for at least one transfer mapping in the set of transfer mappings using a statistical model. At least one transfer mapping is selected based on the score and used to construct the output semantic structure.
    Type: Grant
    Filed: March 30, 2004
    Date of Patent: September 22, 2009
    Assignee: Microsoft Corporation
    Inventors: Anthony Aue, Eric K. Ringger, Christopher B. Quirk, Arul A. Menezes, Robert C. Moore
  • Patent number: 7577562
    Abstract: In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
    Type: Grant
    Filed: December 16, 2004
    Date of Patent: August 18, 2009
    Assignee: Microsoft Corporation
    Inventors: Arul A. Menezes, Christopher B. Quirk, Colin A. Cherry
  • Patent number: 7505894
    Abstract: In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
    Type: Grant
    Filed: December 16, 2004
    Date of Patent: March 17, 2009
    Assignee: Microsoft Corporation
    Inventors: Arul A. Menezes, Christopher B. Quirk, Colin A. Cherry
  • Patent number: 7496496
    Abstract: A machine translation system is trained to generate confidence scores indicative of a quality of a translation result. A source string is translated with a machine translator to generate a target string. Features indicative of translation operations performed are extracted from the machine translator. A trusted entity-assigned translation score is obtained and is indicative of a trusted entity-assigned translation quality of the translated string. A relationship between a subset of the extracted features and the trusted entity-assigned translation score is identified.
    Type: Grant
    Filed: March 19, 2007
    Date of Patent: February 24, 2009
    Assignee: Microsoft Corporation
    Inventors: Christopher B. Quirk, Arul A. Menezes, Stephen D. Richardson, Robert C. Moore
  • Patent number: 7464334
    Abstract: In an operating system, a resource handler accepts resource requests from application modules. A resource request identifies a module from which the requested resource is to be obtained. Rather than providing the resource from the identified module, however, the resource handler provides the requested resource from an associated resource module. An association between an executable module and resource modules of different languages is created by a defined file naming convention, optionally using different directories for resource modules of different languages. Some executable modules contain a shared resource reference which can be used to create an association between multiple executable modules and a single set of shared resource modules. A language fallback mechanism allows alternative languages to be used where resource modules of the appropriate language are not available.
    Type: Grant
    Filed: January 27, 2004
    Date of Patent: December 9, 2008
    Assignee: Microsoft Corporation
    Inventors: Edward S. Miller, Bjorn C. Retting, Gregory Wilson, Shan Xu, Arul A. Meneze, Michael J. Thomson, Sharad Mathur, Roberto Cazzaro, Michael Ginsberg
  • Publication number: 20080154848
    Abstract: The present invention may be used to analyze subject content, search and analyze reference content, compare the subject and reference content for similarity, and output comparison reports between the subject and reference content. The present invention may incorporate and utilize text from intrinsic and/or extrinsic subject documents. The analysis may employ a variety of metrics, including scores generated from a natural language processing system, scores based on classification similarity, scores based on proximity similarity, and in the case of analysis of patent documents, scores based on measurement of claims.
    Type: Application
    Filed: December 20, 2006
    Publication date: June 26, 2008
    Applicant: Microsoft Corporation
    Inventors: Brian Dean Haslam, Patrick Wayne John Evans, Arul Menezes, Patrick Joseph Dinio Santos
  • Publication number: 20070255550
    Abstract: A method of translation includes uploading a source text portion to a back end processor. The back end processor identifies a subset of translation knowledge associated with the source text portion. The back end processor downloads the subset to a front end processor. A translation engine runs on the front end processor. The translation engine generates a translation of the source text portion as a function of the subset.
    Type: Application
    Filed: May 1, 2006
    Publication date: November 1, 2007
    Applicant: Microsoft Corporation
    Inventors: Arul Menezes, Christopher Quirk, Richard Rashid, Robert Moore
  • Publication number: 20070219774
    Abstract: A machine translation system is trained to generate confidence scores indicative of a quality of a translation result. A source string is translated with a machine translator to generate a target string. Features indicative of translation operations performed are extracted from the machine translator. A trusted entity-assigned translation score is obtained and is indicative of a trusted entity-assigned translation quality of the translated string. A relationship between a subset of the extracted features and the trusted entity-assigned translation score is identified.
    Type: Application
    Filed: March 19, 2007
    Publication date: September 20, 2007
    Applicant: Microsoft Corporation
    Inventors: Christopher Quirk, Arul Menezes, Stephen Richardson, Robert Moore
  • Patent number: 7233892
    Abstract: A method of training a natural language processing unit applies a candidate learning set to at least one component of the natural language unit. The natural language unit is then used to generate a meaning set from a first corpus. A second meaning set is generated from a second corpus using a second natural language unit and the two meaning sets are compared to each other to form a score for the candidate learning set. This score is used to determine whether to modify the natural language unit based on the candidate learning set.
    Type: Grant
    Filed: August 15, 2005
    Date of Patent: June 19, 2007
    Assignee: Microsoft Corporation
    Inventors: Eric D. Brill, Arul A. Menezes
  • Patent number: 7209875
    Abstract: A machine translation system is trained to generate confidence scores indicative of a quality of a translation result. A source string is translated with a machine translator to generate a target string. Features indicative of translation operations performed are extracted from the machine translator. A trusted entity-assigned translation score is obtained and is indicative of a trusted entity-assigned translation quality of the translated string. A relationship between a subset of the extracted features and the trusted entity-assigned translation score is identified.
    Type: Grant
    Filed: December 4, 2002
    Date of Patent: April 24, 2007
    Assignee: Microsoft Corporation
    Inventors: Christopher B. Quirk, Arul A. Menezes, Steven D. Richardson, Robert C. Moore
  • Patent number: 7200550
    Abstract: In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
    Type: Grant
    Filed: December 16, 2004
    Date of Patent: April 3, 2007
    Assignee: Microsoft Corporation
    Inventors: Arul A. Menezes, Christopher B. Quirk, Colin A. Cherry
  • Publication number: 20060111892
    Abstract: In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
    Type: Application
    Filed: December 16, 2004
    Publication date: May 25, 2006
    Applicant: Microsoft Corporation
    Inventors: Arul Menezes, Christopher Quirk, Colin Cherry
  • Publication number: 20060111891
    Abstract: In one embodiment of the present invention, a decoder receives a dependency tree as a source language input and accesses a set of statistical models that produce outputs combined in a log linear framework. The decoder also accesses a table of treelet translation pairs and returns a target dependency tree based on the source dependency tree, based on access to the table of treelet translation pairs, and based on the application of the statistical models.
    Type: Application
    Filed: December 16, 2004
    Publication date: May 25, 2006
    Applicant: Microsoft Corporation
    Inventors: Arul Menezes, Christopher Quirk, Colin Cherry