Patents by Inventor David A. Ferrucci
David A. Ferrucci 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: 20130019286Abstract: A method of validating that a user is human. A user question is generated using a computerized device. The user question is output to a user. A user response to the user question is received from the user. The user response is validated as having been provided by a human.Type: ApplicationFiled: August 1, 2012Publication date: January 17, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Michael A. Barborak, Jennifer Chu-Carroll, David A. Ferrucci, James W. Murdock, IV, Wlodek W. Zadrozny
-
Publication number: 20130013547Abstract: Evidence profiling, in one aspect, may receive a candidate answer and supporting pieces of evidence. An evidence profile may be generated, the evidence profile communicating a degree to which the evidence supports the candidate answer as being correct. The evidence profile may provide dimensions of evidence, and each dimension may support or refute the candidate answer as being correct.Type: ApplicationFiled: September 14, 2012Publication date: January 10, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, Jennifer Chu-Carroll, James J. Fan, David A. Ferrucci, David C. Gondek, Anthony T. Levas, James W. Murdock, IV
-
Publication number: 20130013615Abstract: A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving an input query, identifying a plurality of candidate answers to the query; and for at least one of these candidate answers, identifying at least one proof of the answer. This proof includes a series of premises, and a multitude of documents are identified that include references to the premises. A set of these documents is selected that include references to all of the premises. This set of documents is used to generate one or more scores for the one of the candidate answers. A defined procedure is applied to the candidate answers to determine a ranking for the answers, and this includes using the one or more scores for the at least one of the candidate answers in the defined procedure to determine the ranking for this one candidate answer.Type: ApplicationFiled: September 14, 2012Publication date: January 10, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, Jennifer Chu-Carroll, David A. Ferrucci, James W. Murdock, IV
-
Publication number: 20130007055Abstract: A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving an input query; conducting a search to identify candidate answers to the input query, and producing a plurality of scores for each of the candidate answers. For each of the candidate answers, one, of a plurality of candidate ranking functions, is selected. This selected ranking function is applied to the each of the candidate answers to determine a ranking for the candidate answer based on the scores for that candidate answer. One or more of the candidate answers is selected, based on the rankings for the candidate answers, as one or more answers to the input query. In an embodiment, the ranking function selection is performed using information about the question. In an embodiment, the ranking function selection is performed using information about each answer.Type: ApplicationFiled: September 13, 2012Publication date: January 3, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, David A. Ferrucci, James W. Murdock, IV
-
Publication number: 20130007033Abstract: Providing answers to questions based on any corpus of data implements a method that generates a number of candidate passages from the corpus that answer an input query, and finds the correct resulting answer by collecting supporting evidence from the multiple passages. By analyzing all retrieved passages and that passage's metadata in parallel, an output plurality of data structures is generated including candidate answers based upon the analyzing. Then, supporting passage retrieval operations are performed upon the set of candidate answers, and for each candidate answer, the data corpus is traversed to find those passages having candidate answer in addition to query terms. All candidate answers are automatically scored by a plurality of scoring modules, each producing a module score. The modules scores are processed to determine one or more query answers; and, a query response is generated based on the one or more query answers.Type: ApplicationFiled: September 12, 2012Publication date: January 3, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, David Ferrucci, Adam Lally, Wlodek W. Zadrozny
-
Publication number: 20130006641Abstract: A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving an input query, decomposing the input query into a plurality of different subqueries, and conducting a search in one or more data sources to identify at least one candidate answer to each of the subqueries. A ranking function is applied to each of the candidate answers to determine a ranking for each of these candidate answers; and for each of the subqueries, one of the candidate answers to the subquery is selected based on this ranking. A logical synthesis component is applied to synthesize a candidate answer for the input query from the selected the candidate answers to the subqueries. In one embodiment, the procedure applied by the logical synthesis component to synthesize the candidate answer for the input query is determined from the input query.Type: ApplicationFiled: September 14, 2012Publication date: January 3, 2013Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, Jennifer Chu-Carroll, David A. Ferrucci, Adam P. Lally, James W. Murdock, IV, John M. Prager
-
Publication number: 20120330934Abstract: A system, method and computer program product for conducting questions and answers with deferred type evaluation based on any corpus of data. The method includes processing a query including waiting until a “Type” (i.e. a descriptor) is determined AND a candidate answer is provided. Then, a search is conducted to look (search) for evidence that the candidate answer has the required Lexical Answer Type (e.g., as determined by a matching function that can leverage a parser, a semantic interpreter and/or a simple pattern matcher). Prior to or during candidate answer evaluation, a process is provided for extracting and storing collections of entity-type pairs from semi-structured text documents. During QA processing and candidate answer scoring, a process is implemented to match the query LAT against the lexical type of each provided candidate answer and generate a score judging a degree of match.Type: ApplicationFiled: September 6, 2012Publication date: December 27, 2012Applicant: International Business Machines CorporationInventors: Pablo A. Duboue, James J. Fan, David A. Ferrucci, James W. Murdock, IV, Christopher A. Welty, Wlodek W. Zadrozny
-
Publication number: 20120331003Abstract: A system, method and computer program product for efficiently retrieving relevant passages to questions based on a corpus of data. A processor device receives an input query and performs a query analysis to obtain searchable query terms. The processor performs: matching metadata associated with one or more documents against the query terms. The document metadata includes one or more of: a title of the documents, one or more user tags or clouds. Then the processor device performs: mapping matched document metadata to corresponding one or more documents; identifying corresponding matched documents to form a subcorpus of documents; and conducting a search in the data subcorpus using the searchable query terms to obtain one or more passages relevant input query from the identified documents.Type: ApplicationFiled: September 6, 2012Publication date: December 27, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Jennifer Chu-Carroll, David A. Ferrucci
-
Publication number: 20120330921Abstract: A computer-implemented system, method and program product generates answers to questions in an input query text string. The method includes determining, by a programmed processor unit, a lexical answer type (LAT) string associated with an input query; automatically obtaining a candidate answer string to the input query from a data corpus; mapping the query LAT string to a first type string in a structured resource; mapping the candidate answer string to a second type string in the structured resource; and determining if the first type string and the second type string are disjointed; and scoring the candidate answer string based on the determination of the types being disjointed wherein the structured resource includes a semantic database providing ontological content.Type: ApplicationFiled: September 6, 2012Publication date: December 27, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: David A. Ferrucci, Aditya A. Kalyanpur, James W. Murdock, IV, Christopher A. Welty, Wlodek W. Zadrozny
-
Publication number: 20120330648Abstract: Context-based disambiguation of acronyms and/or abbreviations may determine a target abbreviation and one or more keywords appearing in context with the target abbreviation in a received passage, the target abbreviation representing a shortened form of one or more word. A contextual search query including the target abbreviation and said one or more keywords may be generated. A pseudo document index may be searched for one or more expansions of the target abbreviation by invoking the contextual search query, the pseudo document index containing index of one or more pseudo documents, associated one or more abbreviations and associated context keywords. One or more pseudo documents associated with the target abbreviation may be returned based on the searching of the pseudo document index.Type: ApplicationFiled: September 6, 2012Publication date: December 27, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Branimir K. Boguraev, Jennifer Chu-Carroll, David A. Ferrucci, Anthony T. Levas, John M. Prager
-
Publication number: 20120329032Abstract: A system, program product, and methodology automatically scores candidate answers to questions in a question and answer system. In the candidate answer scoring method, a processor device performs one or more of receiving one or more candidate answers associated with a query string, the candidates obtained from a data source having semi-structured content; identifying one or more documents with semi-structured content from the data source having a candidate answer; and for each identified document: extracting one or more entity structures embedded in the identified document; determining a number of the entity structures in the identified document that appear in the received input query; and, computing a score for a candidate answer in the document as a function of the number Overall system efficiency is improved by giving the correct candidate answers higher scores through leveraging context-dependent structural information such as links to other documents and embedded tags.Type: ApplicationFiled: September 6, 2012Publication date: December 27, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: James J. Fan, David A. Ferrucci
-
Publication number: 20120330882Abstract: A system and a computer program product for verifying a statement are provided. The system is configured to receive a statement. The system is configured to decompose the received statement into one or more sets of question and answer pairs. The system is configured to determine a confidence value of each answer in the one or more question and answer pair sets. The system is configured to combine the determined confidence values. The combined confidence values represent a probability that the received statement is evaluated as true.Type: ApplicationFiled: August 31, 2012Publication date: December 27, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: David A. Ferrucci, David C. Gondek, Aditya A. Kalyanpur, Adam P. Lally, Siddharth Patwardhan
-
Publication number: 20120323906Abstract: A system, method and computer program product for automatically estimating the confidence of a detected LAT to provide a more accurate overall score for an obtained candidate answer. A confidence “score” or value of each detected LAT is obtained, and the system and method performs combining the confidence score with a degree of match between a LAT and an AnswerType of the candidate answer to provide improved overall score for the candidate answer.Type: ApplicationFiled: August 29, 2012Publication date: December 20, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: James J. Fan, David A. Ferrucci, David C. Gondek, Aditya A. Kalyanpur, Adam P. Lally, James W. Murdock, Wlodek W. Zadrozny
-
Patent number: 8332394Abstract: A system, method and computer program product for conducting questions and answers with deferred type evaluation based on any corpus of data. The method includes processing a query including waiting until a “Type” is determined AND a candidate answer is provided; the Type is not required as part of a predetermined ontology but is a lexical/grammatical item. Then, a search is conducted for evidence that the candidate answer has the required LAT (e.g., as determined by a matching function leveraging a parser, a semantic interpreter and/or a pattern matcher). Alternately, the LAT may be matched to a known Ontological Type and then a candidate answer searched in an knowledge-base or database determined by that type. Then, all the evidence from all the different ways to determine that the candidate answer has the expected lexical answer type (LAT) is combined and one or more answers provided.Type: GrantFiled: May 23, 2008Date of Patent: December 11, 2012Assignee: International Business Machines CorporationInventors: James Fan, David Ferrucci, David C. Gondek, Wlodek W. Zadrozny
-
Publication number: 20120301864Abstract: Systems and methods display at least one subject, and display a location for at least one user to enter at least one problem related to the subject. The problem comprises unknown items to which the user would like more information. In response to the problem, such systems and methods automatically generate evidence topics related to the problem, and automatically generate questions related to the problem and the evidence topics. Further, such systems and methods can receive additional questions from the user. In response to the questions, such systems and methods automatically generate answers to the questions by referring to sources, automatically calculate confidence measures of each of the answers, and then display the questions, the answers, and the confidence measures. When the user identifies one of the answers as a selected answer, such systems and methods display details of the sources and the factors used to generate the selected answer.Type: ApplicationFiled: April 17, 2012Publication date: November 29, 2012Applicant: International Business Machines CorporationInventors: Sugato Bagchi, Michael A. Barborak, Steven D. Daniels, David A. Ferrucci, Anthony T. Levas
-
Patent number: 8280838Abstract: An evidence evaluation method and system based on question answering converts a report of analyzed information and/or a model of information into a collection of questions, determines answers for the collection of questions. A fact in the report is marked as being supported if one or more of the answers for the collection of questions support the fact. A fact in the report of analyzed facts is marked as being refuted if one or more of the answers for the collection of questions refute the fact. The method and system also may collect the answers as evidence and add the evidence to the model of information to create an updated model of information. The steps may be repeated using the updated report and updated model.Type: GrantFiled: September 17, 2009Date of Patent: October 2, 2012Assignee: International Business Machines CorporationInventors: David A. Ferrucci, Wlodek W. Zadrozny
-
Patent number: 8275803Abstract: A system, method and computer program product for providing answers to questions based on any corpus of data. The method facilitates generating a number of candidate passages from the corpus that answer an input query, and finds the correct resulting answer by collecting supporting evidence from the multiple passages. By analyzing all retrieved passages and that passage's metadata in parallel, there is generated an output plurality of data structures including candidate answers based upon the analyzing. Then, by each of a plurality of parallel operating modules, supporting passage retrieval operations are performed upon the set of candidate answers, and for each candidate answer, the data corpus is traversed to find those passages having candidate answer in addition to query terms. All candidate answers are automatically scored causing the supporting passages by a plurality of scoring modules, each producing a module score.Type: GrantFiled: May 14, 2008Date of Patent: September 25, 2012Assignee: International Business Machines CorporationInventors: Eric W. Brown, David Ferrucci, Adam Lally, Wlodek W. Zadrozny
-
Patent number: 8200656Abstract: A method, system and computer program product are disclosed for searching for information using a knowledge base. In one embodiment, the method comprises receiving a query; formulizing the query, including dividing the query into a plurality of parts; for each of the parts, identifying a source, using the knowledge, that addresses that part; and combining the sources to answer the query. In one embodiment, the query includes text; the text is separated into a plurality of segments; and, for each of the segments, at least one source is identified addressing the segment. In an embodiment, a logical proof is formulated having a conclusion that is an answer to the query, and a sequence of statements that establish said conclusion; and a proof of this conclusion is generated by identifying two or more documents that assert the sequence of statements.Type: GrantFiled: November 17, 2009Date of Patent: June 12, 2012Assignee: International Business Machines CorporationInventors: Eric W. Brown, Jennifer Chu-Carroll, James J. Fan, David A. Ferrucci, David C. Gondek, Anthony T. Levas, James William Murdock, IV
-
Publication number: 20120131016Abstract: Evidence profiling, in one aspect, may receive a candidate answer and supporting pieces of evidence. An evidence profile may be generated, the evidence profile communicating a degree to which the evidence supports the candidate answer as being correct. The evidence profile may provide dimensions of evidence, and each dimension may support or refute the candidate answer as being correct.Type: ApplicationFiled: September 23, 2011Publication date: May 24, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Eric W. Brown, Jennifer Chu-Carroll, James J. Fan, David A. Ferrucci, David C. Gondek, Anthony T. Levas, James W. Murdock, IV
-
Publication number: 20120089622Abstract: A system, program product, and methodology automatically scores candidate answers to questions in a question and answer system. In the candidate answer scoring method, a processor device performs one or more of receiving one or more candidate answers associated with a query string, the candidates obtained from a data source having semi-structured content; identifying one or more documents with semi-structured content from the data source having a candidate answer; and for each identified document: extracting one or more entity structures embedded in the identified document; determining a number of the entity structures in the identified document that appear in the received input query; and, computing a score for a candidate answer in the document as a function of the number Overall system efficiency is improved by giving the correct candidate answers higher scores through leveraging context-dependent structural information such as links to other documents and embedded tags.Type: ApplicationFiled: September 24, 2011Publication date: April 12, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: James J. Fan, David A. Ferrucci