Patents by Inventor Joy Mustafi

Joy Mustafi 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: 9514185
    Abstract: A method providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP) is provided. The method may include receiving the input question. The method may also include performing natural language processing (NLP) analysis on the input question to extract a required value phrase. The method may further include forming at least one mathematical equation based on the extracted required value phrase. Additionally, the method may include forming at least one interim question based on the extracted required value phrase. The method may further include solving the at least one formed mathematical equation and the at least one formed interim question. The method may also include narrating the answer to the input question in natural language based on the solved at least one interim question or the solved at least one mathematical equation.
    Type: Grant
    Filed: August 7, 2014
    Date of Patent: December 6, 2016
    Assignee: International Business Machines Corporation
    Inventors: Ashish Mungi, Joy Mustafi
  • Patent number: 9495355
    Abstract: A method for solving and answering an arithmetic or algebraic problem using natural language processing (NLP) is provided. The method may include receiving an input statement associated with the arithmetic or algebraic problem. The method may also include determining whether each sentence within a plurality of sentences associated with the input statement is a well-formed sentence from a mathematical perspective. The method may further include converting each statement into a well-formed sentence based on the determining whether each sentence within a plurality of sentences associated with the input statement is a well-formed sentence from a mathematical perspective. Additionally, the method may include converting each well-formed sentence into a mathematical equation to form a set of equations. Also, the method may include solving the set of equations to compute a mathematical result. The method may include narrating the mathematical result in natural language.
    Type: Grant
    Filed: August 29, 2014
    Date of Patent: November 15, 2016
    Assignee: International Business Machines Corporation
    Inventors: Ashish Mungi, Joy Mustafi
  • Publication number: 20160314106
    Abstract: Machine logic that automatically detects natural language processing (NLP) system annotation errors and correspondingly updates NLP annotators to prevent future erroneous annotations by performing the following steps: (i) determining that a first annotation error has occurred in an annotation of a corpus by the natural language processing system; (ii) generating a candidate set of annotation correction actions, where each annotation correction action of the set is adapted to prevent an occurrence of an error similar to the first annotation error by the natural language processing system; (iii) selecting an annotation correction action from the candidate set of annotation correction actions, based, at least in part, on a set of annotation correction confidence characteristics; and (iv) automatically applying the selected annotation correction action to the natural language processing system.
    Type: Application
    Filed: April 27, 2015
    Publication date: October 27, 2016
    Inventors: Scott R. Carrier, Joy Mustafi, Anil M. Omanwar, Avinesh Polisetty Venkata Sai
  • Publication number: 20160300139
    Abstract: A method providing an answer to at least one analytical question containing at least one table or at least one chart is provided. The method may include receiving an input question. The method may also include extracting a plurality of information from the input question based on a natural language analysis. The method may further include forming a well-defined sentence. The method may include extracting at least one table or at least one chart associated with the input question. The method may include forming at least one mathematical equation. The method may also include solving the at least one mathematical equation. The method may include determining the answer to the input question in natural language based on the solved at least one mathematical equation. The method may further include narrating the determined answer to the input question in natural language.
    Type: Application
    Filed: June 21, 2016
    Publication date: October 13, 2016
    Inventors: Sandesh Bhat, Joy Mustafi
  • Publication number: 20160299963
    Abstract: A method providing an answer to at least one analytical question containing at least one table or at least one chart is provided. The method may include receiving an input question. The method may also include extracting a plurality of information from the input question based on a natural language analysis. The method may further include forming a well-defined sentence. The method may include extracting at least one table or at least one chart associated with the input question. The method may include forming at least one mathematical equation. The method may also include solving the at least one mathematical equation. The method may include determining the answer to the input question in natural language based on the solved at least one mathematical equation. The method may further include narrating the determined answer to the input question in natural language.
    Type: Application
    Filed: June 21, 2016
    Publication date: October 13, 2016
    Inventors: Sandesh Bhat, Joy Mustafi
  • Publication number: 20160293034
    Abstract: Generating distractors for text-based MCT items. An MCT item stem is received. The stem is transmitted to a QA system and a plurality of candidate answers related to the stem is received from the QA system. Incorrect answers in the plurality of candidate answers are identified. Textual features are extracted from the stem. A set of semantic criteria associated with the extracted textual features is generated. Based on the generated semantic criteria, a subset of the incorrect candidate answers is selected.
    Type: Application
    Filed: March 30, 2015
    Publication date: October 6, 2016
    Inventors: Lalit Agarwalla, Ashish Mungi, Joy Mustafi, Ankur Parikh
  • Publication number: 20160292593
    Abstract: Generating distractors for text-based MCT items. An MCT item stem is received. The stem is transmitted to a QA system and a plurality of candidate answers related to the stem is received from the QA system. Incorrect answers in the plurality of candidate answers are identified. Textual features are extracted from the stem. A set of semantic criteria associated with the extracted textual features is generated. Based on the generated semantic criteria, a subset of the incorrect candidate answers is selected.
    Type: Application
    Filed: May 20, 2016
    Publication date: October 6, 2016
    Inventors: Lalit Agarwalla, Ashish Mungi, Joy Mustafi, Ankur Parikh
  • Publication number: 20160292153
    Abstract: In one embodiment of the present invention, one or more sections of a document are identified, and segments of text within the one or more sections are parsed. The parsed segments of text are analyzed to identify parsed segments of text associated with pointers indicative of example content. One or more links are generated between the identified parsed segments of text and one or more topics to which they pertain. Embodiments of the present invention can be used, for example, to increase accuracy of search results by identifying examples in documents returned as search results, as well as by filtering out examples that may cause the main content of text to be obscured in the search results.
    Type: Application
    Filed: March 31, 2015
    Publication date: October 6, 2016
    Inventors: Lalit Agarwalla, Amit P. Bohra, Joy Mustafi, Ankur S. Parikh
  • Patent number: 9460075
    Abstract: A computer system for solving and answering an arithmetic or algebraic problem using natural language processing (NLP) is provided. The computer system may include receiving an input statement associated with the arithmetic or algebraic problem. The computer system may also include determining whether each sentence within a plurality of sentences associated with the input statement is a well-formed sentence from a mathematical perspective. The computer system may further include converting each statement into a well-formed sentence based on the determining whether each sentence within a plurality of sentences associated with the input statement is a well-formed sentence from a mathematical perspective. Additionally, the computer system may include converting each well-formed sentence into a mathematical equation to form a set of equations. Also, the computer system may include solving the set of equations to compute a mathematical result.
    Type: Grant
    Filed: June 17, 2014
    Date of Patent: October 4, 2016
    Assignee: International Business Machines Corporation
    Inventors: Ashish Mungi, Joy Mustafi
  • Patent number: 9430557
    Abstract: A method providing an answer to at least one analytical question containing at least one table or at least one chart is provided. The method may include receiving an input question. The method may also include extracting a plurality of information from the input question based on a natural language analysis. The method may further include forming a well-defined sentence. The method may include extracting at least one table or at least one chart associated with the input question. The method may include forming at least one mathematical equation. The method may also include solving the at least one mathematical equation. The method may include determining the answer to the input question in natural language based on the solved at least one mathematical equation. The method may further include narrating the determined answer to the input question in natural language.
    Type: Grant
    Filed: September 17, 2014
    Date of Patent: August 30, 2016
    Assignee: International Business Machines Corporation
    Inventors: Sandesh Bhat, Joy Mustafi
  • Patent number: 9430558
    Abstract: A method providing an answer to at least one analytical question containing at least one table or at least one chart is provided. The method may include receiving an input question. The method may also include extracting a plurality of information from the input question based on a natural language analysis. The method may further include forming a well-defined sentence. The method may include extracting at least one table or at least one chart associated with the input question. The method may include forming at least one mathematical equation. The method may also include solving the at least one mathematical equation. The method may include determining the answer to the input question in natural language based on the solved at least one mathematical equation. The method may further include narrating the determined answer to the input question in natural language.
    Type: Grant
    Filed: April 8, 2015
    Date of Patent: August 30, 2016
    Assignee: International Business Machines Corporation
    Inventors: Sandesh Bhat, Joy Mustafi
  • Patent number: 9330084
    Abstract: During ingestion of non-natural language text content into a knowledge base, a question answering computing system (QA system) converts the content into natural language text. The QA system identifies natural language sentences in the content and converts the sentences into well-formed simple sentences by resolving grammatical ambiguities in the sentences. The QA system then generates question-answer pairs (QA pairs) from the well-formed simple sentence and stores the QA pairs in a persistent store.
    Type: Grant
    Filed: December 10, 2014
    Date of Patent: May 3, 2016
    Assignee: International Business Machines Corporation
    Inventors: Shreesha Kadambi, Ashish Mungi, Joy Mustafi, Vani Singh
  • Publication number: 20160078772
    Abstract: A method providing an answer to at least one analytical question containing at least one table or at least one chart is provided. The method may include receiving an input question. The method may also include extracting a plurality of information from the input question based on a natural language analysis. The method may further include forming a well-defined sentence. The method may include extracting at least one table or at least one chart associated with the input question. The method may include forming at least one mathematical equation. The method may also include solving the at least one mathematical equation. The method may include determining the answer to the input question in natural language based on the solved at least one mathematical equation. The method may further include narrating the determined answer to the input question in natural language.
    Type: Application
    Filed: April 8, 2015
    Publication date: March 17, 2016
    Inventors: Sandesh Bhat, Joy Mustafi
  • Publication number: 20160078127
    Abstract: A method providing an answer to at least one analytical question containing at least one table or at least one chart is provided. The method may include receiving an input question. The method may also include extracting a plurality of information from the input question based on a natural language analysis. The method may further include forming a well-defined sentence. The method may include extracting at least one table or at least one chart associated with the input question. The method may include forming at least one mathematical equation. The method may also include solving the at least one mathematical equation. The method may include determining the answer to the input question in natural language based on the solved at least one mathematical equation. The method may further include narrating the determined answer to the input question in natural language.
    Type: Application
    Filed: September 17, 2014
    Publication date: March 17, 2016
    Inventors: Sandesh Bhat, Joy Mustafi
  • Publication number: 20160041980
    Abstract: A method providing an answer to an input question containing at least one time-sensitive word or at least one time-sensitive phrase using natural language processing (NLP) is provided. The method may include receiving the input question. The method may also include performing natural language processing (NLP) analysis on the input question to extract a required value phrase. The method may further include forming at least one mathematical equation based on the extracted required value phrase. Additionally, the method may include forming at least one interim question based on the extracted required value phrase. The method may further include solving the at least one formed mathematical equation and the at least one formed interim question. The method may also include narrating the answer to the input question in natural language based on the solved at least one interim question or the solved at least one mathematical equation.
    Type: Application
    Filed: August 7, 2014
    Publication date: February 11, 2016
    Inventors: Ashish Mungi, Joy Mustafi
  • Publication number: 20150363390
    Abstract: A computer system for solving and answering an arithmetic or algebraic problem using natural language processing (NLP) is provided. The computer system may include receiving an input statement associated with the arithmetic or algebraic problem. The computer system may also include determining whether each sentence within a plurality of sentences associated with the input statement is a well-formed sentence from a mathematical perspective. The computer system may further include converting each statement into a well-formed sentence based on the determining whether each sentence within a plurality of sentences associated with the input statement is a well-formed sentence from a mathematical perspective. Additionally, the computer system may include converting each well-formed sentence into a mathematical equation to form a set of equations. Also, the computer system may include solving the set of equations to compute a mathematical result.
    Type: Application
    Filed: June 17, 2014
    Publication date: December 17, 2015
    Inventors: Ashish Mungi, Joy Mustafi
  • Publication number: 20150363391
    Abstract: A method for solving and answering an arithmetic or algebraic problem using natural language processing (NLP) is provided. The method may include receiving an input statement associated with the arithmetic or algebraic problem. The method may also include determining whether each sentence within a plurality of sentences associated with the input statement is a well-formed sentence from a mathematical perspective. The method may further include converting each statement into a well-formed sentence based on the determining whether each sentence within a plurality of sentences associated with the input statement is a well-formed sentence from a mathematical perspective. Additionally, the method may include converting each well-formed sentence into a mathematical equation to form a set of equations. Also, the method may include solving the set of equations to compute a mathematical result. The method may include narrating the mathematical result in natural language.
    Type: Application
    Filed: August 29, 2014
    Publication date: December 17, 2015
    Inventors: Ashish Mungi, Joy Mustafi