International Business Machines Corporation

Elemental Cognition LLC

Prios, LLC

Nuance Communications, Inc.

Elmental Cognition LLC

David Angelo Ferrucci

Jennifer Chu-Carroll

James W Murdock, Iv

Aditya Anand Kalyanpur

Eric William Brown

Adam P Lally

Wlodek Wlodzimierz Zadrozny

David C Gondek

Anthony Tom Levas

James J Fan

David W Buchanan

Sugato Bagchi

John Martin Prager

Chang Wang

Mike Barborak

Greg Burnham

Adam Lally

Stefano Pacifico

James William Murdock, Iv

Branimir Konstantinov Boguraev

Christopher A Welty

Erik Thomas Mueller

Michael A Barborak

Youssef Drissi

Paul Turquand Keyser

Siddharth A Patwardhan

Shirin Saleem

Alfio Massimiliano Gliozzo

Steven R Abrams

Dafna Sheinwald

Steinar Flatland

Pablo Ariel Duboue

Vincent L Marshall

Ray Dalio

David Melville

Jose Barrera

Gregory H Burnham

Lei Zhang

Chen Wang

Murthy V Devarakonda

Genady Grabarnik

Yurdaer Nezihi Doganata

David Carmel

Yoelle Smadja Maarek

Li Li Ma

Lev Kozakov

Yue Pan

Andrew Aaron

Yosi Mass

Aya Soffer

Tong-Haing Fin

Andrei Zary Broder

Zhao Ming Qiu

John Ferdinand Pitrelli

Arthur Charles Ciccolo

Keerthana Boloor

Steven D Daniels

Clifton James McFate

Selmer Conrad Bringsjord

James C Murdock, Iv

Andrea Bradshaw

Thomas Breloff

Siddharth Patwardham

Or Biran

Kailash Karthik Saravanakumar

A reading comprehension system may include an authoring tool to help generate adaptable dialogs and a reading tool to conduct adaptable dialog sessions with students. The authoring tool may receive and process stories to generate labeled stories and information models. The information models may provide the conceptual structures that an effective reader should build while reading and understanding a story. The system may use dialog models for general dialogs and information models for story specific dialogs to guide adaptable dialog sessions with students. During the adaptable dialog sessions, the system may constantly assess and guide the student's progress in the understanding the current story and in general reading comprehension development. Using the labeled stories and dialog sessions as training data, the system may learn how to dialog effectively with the students, to gather an evolving understanding of the student's abilities, and to acquire knowledge about the world or the story.

Information and dialog models for education

A meta model may be provided as a global structure providing flexible or customizable options for a specific ontology designed by a system operator. A meta model may include generic structures, such as attributes, attribute categories, and attribute properties. A system operator may configure a set of specific attributes, attribute categories, and synthesis rules within the meta model to define a desired ontology, customizing the system to a specific purpose. A system can receive assertions about points of interest known to the system, and store information about attributes of points of interest based on the specified ontology.

Gathering and analyzing assessment data using customizable ontologies built upon a meta model

A research assistant system may include a research tool and components and a user interface to discover and evidence answers to complex research questions. The research tools may include components to iteratively perform steps in a research process, including searching, analyzing, connecting, aggregating, synthesizing, and chaining together evidence from a diverse set of knowledge sources. The system may receive an input query and perform a semantic search for key concepts in a text corpus. A semantic parser may interpret the search results. The system may aggregate and synthesize information from interpreted results. The system may rank and score the aggregated results data and present data on the user interface. The user interface may include prompts to iteratively guide user input to explore evidentiary chains and connect research concepts to produce research results annotated by evidence passages.

Interactive research assistant—multilink

A dynamic reasoning system may include a symbolic reasoning engine that iteratively calls a dynamic rule generator to answer an input query. The symbolic reasoning engine may determine a primary goal and/or secondary goals to generate proofs for the answer. The symbolic reasoning engine may call a rules component to provide rules to prove a current input goal. The rules component may use a static rule knowledge base and/or the dynamic rule generator to retrieve and rank rules relevant to the current input goal. The dynamic rule generator may generate new rules that lead to the current input goal. The dynamic rule generator may include a statistical model that generates unstructured or structured probabilistic rules based on context related to the input query. The symbolic reasoning engine may return a list of rules with confidence for explaining the answer to the input goal.

Knowledge representation and reasoning system and method using dynamic rule generator

Interactive research assistant&#x2014;life science

Interactive research assistant&#x2014;user interface/user experience (UI/UX)

A natural language interfacing system may use a knowledge acquisition tool to obtain structured representations from user input text. The system may initiate interaction with a request for input and a partial statement with blank text slots labeled by field types. The system may receive input text to fill in a slot of the partial statement and perform semantic parsing on the input text to identify a trigger concept. The system may generate a list of templates defining different semantic frames for the trigger concept. A generated template may include additional generated slots and/or suggested slot-fillers to guide user input. In response to a template selection, the partial statement includes the trigger concept annotated with a semantic frame. This process is repeated by iteratively updating the list of templates until the statement is completed. The statement is mapped to a structured representation including semantic frames.

Knowledge acquisition tool

A method, system and computer program product for generating answers to questions. In one embodiment, the method comprises receiving a query, conducting a search through one or more data sources to identify candidate answers to the query, and providing each of the candidate answers with a preliminary score. The method further comprises filtering out any of the candidate answers with a preliminary score that does not satisfy a defined condition. The candidate answers having preliminary scores that satisfy this condition form a subset of the candidate answers. Each of the candidate answers in this subset is processed to produce further scores. A ranking function is applied to these further scores to determine a ranking for each of the candidate answers in the subset; and after this ranking function is applied, one or more of the candidate answers are selected as one or more final answers to the query.

Providing answers to questions using hypothesis pruning

A method for generating inference graphs over content to answer input inquiries. First, independent factors are produced from the inquiry, and these factors are converted to questions. The questions are then input to a probabilistic question answering system (PQA) that discovers relations which are used to iteratively expand an inference graph starting from the factors and ending with possible answers. A probabilistic reasoning system is used to infer the confidence in each answer by, for example, propagating confidences across relations and nodes in the inference graph as it is expanded. The inference graph generator system can be used to simultaneously bi-directionally generate forward and backward inference graphs that uses a depth controller component to limit the generation of both paths if they do not meet. Otherwise, a joiner process forces the discovery of relations that join the answers to factors in the inquiry.

Text-based inference chaining

A method, computer system, and computer program product for decision support is provided. The present invention may include receiving a problem case information and generating a query based on the problem case information. The present invention may also include generating a plurality of answers for the query using the question-answering module. The present invention may also include calculating numerical values for multiple evidence dimensions from evidence sources for each of the answers using the question-answering module and may further include calculating a corresponding confidence value for each of the answers based on the numerical value of each evidence dimension using the question-answering module. The present invention may also include outputting the generated answers, the corresponding confidence values, and the numerical values of each evidence dimension for one or more selected answers using the input/output module.

Decision-support application and system for medical differential-diagnosis and treatment using a question-answering system

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.

Providing answers to questions including assembling answers from multiple document segments

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.

Providing answers to questions using logical synthesis of candidate answers

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.

Providing answers to questions using multiple models to score candidate answers

An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.

Architecture and processes for computer learning and understanding

Growing community of inventors

Yorktown Heights, NY, United States of America

David Angelo Ferrucci