International Business Machines Corporation

Adam P Lally

David Angelo Ferrucci

Jennifer Chu-Carroll

Aditya Anand Kalyanpur

David C Gondek

James W Murdock, Iv

Eric William Brown

James William Murdock, Iv

Wlodek Wlodzimierz Zadrozny

John Martin Prager

James J Fan

Benjamin P Segal

Michael Robert Glass

David W Buchanan

Lorrie Ann Tomek

Apoorv Agarwal

Michael A Barborak

Steinar Flatland

Erik Thomas Mueller

Alfio Massimiliano Gliozzo

Md Faisal Mahbub Chowdhury

Siddharth A Patwardhan

Siddharth Patwardham

David A Ferrucci

James C Murdock, Iv

Aditya A Kalyanpur

Wlodek W Zadrozny

Anthony Levas

Iv Murdock James W

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, 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 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 may join the answers to factors in the inquiry.

According to an aspect, a term saliency model is trained to identify salient terms that provide supporting evidence of a candidate answer in a question answering computer system based on a training dataset. The question answering computer system can perform term saliency weighting of a candidate passage to identify one or more salient terms and term weights in the candidate passage based on the term saliency model. The one or more salient terms and term weights can be provided to at least one passage scorer of the question answering computer system to determine whether the candidate passage is justified as providing supporting evidence of the candidate answer.

Identifying salient terms for passage justification in a question answering system

According to an aspect, a processing system of a question answering computer system determines a first set of relations between one or more pairs of terms in a question. The processing system also determines a second set of relations between one or more pairs of terms in a candidate passage including a candidate answer to the question. The processing system matches the first set of relations to the second set of relations. A plurality of scores is determined by the processing system based on the matching. The processing system aggregates the scores to produce an answer score indicative of a level of support that the candidate answer correctly answers the question.

Evaluating passages in a question answering computer system

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 method of answering questions. A word problem is received into a user interface of a question-answering (QA) system operating on a computerized device having a processor. The word problem comprises a question and contextual phrases providing context for the question. The question is parsed from the word problem, using a parsing function of the processor. The contextual phrases are parsed from the word problem, using the parsing function of the processor. A type is identified for the question, using a typing function of the processor. A phrase is identified in the question having the same type as the question. A reformulated question is produced by replacing the phrase in the question having the same type as the question with a contextual phrase. The reformulated question is input to the QA system. Answers to the reformulated question are received from the QA system.

System and method for question answering by reformulating word problems

Growing community of inventors

Cold Spring, NY, United States of America

Adam P Lally