International Business Machines Corporation

University of North Carolina at Charlotte

Other

Wlodek Wlodzimierz Zadrozny

Dimitri Kanevsky

David Angelo Ferrucci

Alexander Zlatsin

James W Murdock, Iv

David C Gondek

James J Fan

Aditya Anand Kalyanpur

Adam P Lally

Jennifer Chu-Carroll

Christopher A Welty

Nandakishore Kambhatla

Michael A Barborak

Eric William Brown

Anthony Tom Levas

Sugato Bagchi

James William Murdock, Iv

Catherine Gody Wolf

Stephane Herman Maes

Jana Helton Jenkins

Sara H Basson

Michelle Yoonkyung Kim

David C Steinmetz

Pablo Ariel Duboue

Clifford A Pickover

Manoj N Kumar

Lei Zhang

David Nahamoo

Murthy V Devarakonda

Michael Alan Picheny

Charles Philippe Tresser

Neal Martin Keller

Marcel Mordechay Yung

Norbert George Vogl

David Carmel

Yoelle Smadja Maarek

Kenneth James Barker

Nikolai A Joukov

Maroun Touma

Jan Sedivy

Yosi Mass

Aya Soffer

Nithya Rajamani

Konstantinos Magoutis

Yiming Ye

Tetsunosuke Fujisaki

Andrei Zary Broder

Apoorv Agarwal

Dragomir Radkov Radev

Judith L Klavans

Arthur Charles Ciccolo

James Rubas

Hamed A Ellozy

Melania Degeratu

Sarah H Basson

Wenwen Dou

Michael Sava

Julian Chengjun Chen

Lisa C Braden-Harder

Seethalakshmi Gopalakrishnan

Victor Zitian Chen

Joyce Yue Chai

Sunil Subramanyam Govindappa

Taufique Samdani

Walid A Shalaby

Vit V Libal

Kripa Rajshekhar

David A Ferucci

Nanda Kambhatla

Nico M Schlaefer

A hypergraph user interface for interaction with a system for integrative causal modeling from natural language text and including a natural language text input element configured to receive a designation of a natural language text file or such a file. The input element causes the designation or natural language text file to be communicated to at least one natural language processing module. The hypergraph user interface further includes a causal hypergraph visualization element representative of directed hypergraph data generated from the at least one natural language processing module. Selection of a hypergraph element of the causal hypergraph representation causes the hypergraph user interface to communicate an indication of the hypergraph element to a querying module and generate an informative element indicative of at least one of a causal link, a causal statement, or a sentence of the at least one natural text file on which the hypergraph element is based.

Computer implemented method and system for integrative causal modeling and transfer

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.

Providing question and answers with deferred type evaluation using text with limited structure

According to an aspect, a heterogeneous graph in a data store is accessed. The heterogeneous graph includes a plurality of nodes having a plurality of node types. The nodes are connected by edges having a plurality of relation types. One or more intermediary graphs are created based on the heterogeneous graph. The intermediary graphs include intermediary nodes that are the relation types of the edges of the heterogeneous graph and include intermediary links between the intermediary nodes based on shared instances of the nodes between relation types in the heterogeneous graph. The intermediary graphs are traversed to find sets of relations based on intermediary links according to a template. An inference rule is extracted from the heterogeneous graph based on finding sets of relations in the intermediary graphs. The inference rule defines an inferred relation type between at least two of the nodes of the heterogeneous graph.

Extraction of inference rules from heterogeneous graphs

A question/answer creation system is described. The system includes a memory device and a processor connected to the memory device. The processor is configured to import a document having a set of questions based on content in the document, automatically create a candidate question from the content in the document, automatically generate answers for the set of questions and the candidate question using the content in the document, present the set of questions, the candidate question, and the answers to a content creator for user verification of accuracy, and store a verified set of questions in the document. The verified set of questions includes at least one verified question from the set of questions and the candidate question.

Content revision using question and answer generation

The present disclosure relates generally to question answering systems and methods and, particularly, to systems and methods for domain adaptation in question answering.

System and method for domain adaptation in question answering

A method for question/answer creation for a document is described. The method includes importing a document having a set of questions based on content in the document. The method also includes automatically creating a candidate question from the content in the document. The method also includes automatically generating answers for the set of questions and the candidate question using the content in the document. The method also includes presenting the set of questions, the candidate question, and the answers to a content creator for user verification of accuracy. The method also includes storing a verified set of questions in the document. The verified set of questions includes the candidate question.

Mined semantic analysis techniques (MSA) include generating a first subset of concepts, from a NL corpus, that are latently associated with an NL candidate term based on (i) a second subset of concepts from the corpus that are explicitly or implicitly associated with the candidate term and (ii) a set of concept association rules. The concept association rules are mined from a transaction dictionary constructed from the corpus and defining discovered latent associations between corpus concepts. A concept space of the candidate term includes at least portions of both the first and second subset of concepts, and includes indications of relationships between latently-associated concepts and the explicitly/implicitly-associated concepts from which the latently-associated concepts were derived. Measures of relatedness between candidate terms are deterministically determined based on their respective concept spaces. Example corpora include digital corpora such as encyclopedias, journals, intellectual property datasets, health-care related datasets/records, financial-sector related datasets/records, etc.

Natural language relatedness tool using mined semantic analysis

A method for providing adaptation to a question answering (QA) system having an associated plurality of trace data and a question-answer set. The method includes submitting a set of questions to the QA system; receiving back from the QA system a set of answers; comparing the set of answers to answers in the question-answer set; and generating the plurality of trace data based on comparison, and an estimate of how much more training data is needed. The generating comprises (a) for each question type, successively sample an increasing number of question-answer pairs from the question-answer set; (b) automatically train the QA system using the sampled question-answer pairs; (c) automatically compute a functional dependence of the QA system performance on the remaining questions relative to the size of the sample; and (d) extrapolate from the functional dependence a number of training question-answer pairs of each question type.

System and method for 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.

System and method for providing answers to questions

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.

Using ontological information in open domain type coercion

A computerized device for enhancing the accuracy of a question-answer system is disclosed. The computerized device comprises a question-answer system comprising software for performing a plurality of question answering processes. A receiver receives a question into the question-answer system. A processor that generates a plurality of candidate answers to the question is connected to the question-answer system. The processor determines a confidence score for each of the plurality of candidate answers. The processor evaluates sources of evidence used to generate the plurality of candidate answers. The processor identifies missing information from a corpus of data. The missing information comprises any information that improves a confidence score for a candidate answer. The processor generates at least one follow-on inquiry based on the missing information. A network interface outputs the at least one follow-on inquiry to external sources separate from the question-answer system.

Utilizing failures in question and answer system responses to enhance the accuracy of question and answer systems

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.

Validating that a user is human

Growing community of inventors

Tarrytown, NY, United States of America

Wlodek Wlodzimierz Zadrozny