International Business Machines Corporation

Benjamin P Segal

Branimir Konstantinov Boguraev

Rajaram B Krishnamurthy

Donald W Schmidt

Carl Joseph Parris

Esme Manandise

Jerry Wayne Stevens

James W Murdock, Iv

Constantinos Kassimis

John Martin Prager

Michael Jon Fox

Bharath Dandala

Lakshminarayanan Krishnamurthy

Hugh Edward Hockett

Timothy P Winkler

Radha Mohan De

Aditya Anand Kalyanpur

James J Fan

Michael G Fitzpatrick

Jeffrey Douglas Haggar

Anthony Tom Levas

Adam P Lally

Michael Robert Glass

David Anthony Herr

Maurice Isrel

David G Chapman

James William Murdock, Iv

Michael A Barborak

Sujoy Roy

Todd Elsworth Valler

Natarajan Krishnaswami

Alper Buyuktosunoglu

Anthony Thomas Sofia

Richard Harold Boivie

Tong Chen

Jason G Katonica

D Gary Chapman

Deborah A Odell

Marcos Barbieri

Esme Manadise

Aspects include receiving a query at a data engine. The data engine includes data in a protected format stored in a secured database and a copy of the data in a clear format stored in a secured database replica. The query is received from a requestor. The query is processed at the secured database replica to generate a query response in the clear format. The query response is converted into the protected format. The converted query response in the protected format is provided to the requestor.

Secure ingress and egress for data engines

A method, system and apparatus for protecting from out of bounds memory references, including establishing a threshold number of active objects for examination for an out of bounds memory reference, determining whether a number of active objects for an application exceeds the threshold, and when the number of active objects exceeds the threshold, storing at least part of information about the active objects in an overflow table in a memory.

Hardware support for memory safety with an overflow table

A method for determining an application error from a screenshot includes receiving, by a computing device, a computer application screenshot image indicating a computer error has occurred. The computing device analyzes the computer application screenshot image using a machine learning image analysis to determine one or more error regions in the computer application screenshot image. The computing device further processes the analyzed computer application screenshot to extract text from the one or more error regions in the computer application screenshot image. The computing device determines the application error based upon the extracted text. The computing device further automatically applies an automated error fix based upon the determined application error.

Application error analysis from screenshot

A method modifies a social media post in response to determining that a hashtag for the social media post diverges from how the hashtag is used by other social media posts. A computing device receives a social media post, which contains a hashtag, and analyzes the social media post using natural language processing and a sentiment analysis to determine a sense and sentiment of the social media post. The computing device receives a plurality of reference social media posts, where each of the reference social media posts contains the hashtag, and utilizes the natural language processing and the sentiment analysis to determine a sense and sentiment of the reference social media posts. In response to determining that the sense and sentiment of the social media post do not match the sense and sentiment of the reference social media posts, the computing device causes the social media post to be altered.

Protecting a social media post with a hashtag from divergence

A computer program product for domain-specific data generation. The computer program product including a computer-readable storage medium having program instructions embodied therewith. The program instructions executable by a processor to cause the processor to perform operations including performing an analysis on a domain-specific corpus to identify a base term and a modifier term. The modifier term modifies the base term in at least a portion of the domain-specific corpus. The operations also include accessing a first entry in lexicon data. The first entry including core data corresponding to domain-independent lexical information for the base term. The operations further include adding, based on the analysis, non-core data to the first entry, the non-core data corresponding to domain-specific lexical information for the base term, wherein the non-core data identifies the modifier term as a domain-specific modifier of the base term.

Domain-specific lexical analysis

A method includes performing, at a device, an analysis of a domain-specific corpus to identify a base term and a modifier term. The modifier term modifies the base term in at least a portion of the domain-specific corpus. The method also includes accessing, by the device, a first entry in lexicon data. The first entry includes core data corresponding to domain-independent lexical information for the base term. The method further includes adding, based on the analysis, non-core data to the first entry. The non-core data corresponds to domain-specific lexical information for the base term. The non-core data identifies the modifier term as a domain-specific modifier of the base term.

Natural language processing (NLP) with awareness of textual polarity. An NLP system, such as a search engine or a Question-Answering (QA) system receives input text for processing. The input text may be a text fragment, a search phrase, a question having a general type, or a polar question having a yes or no answer. The NLP system identifies textual polarity and provides responses to the input text (for example, in answer form) based on identifying evidence whose selection, scoring, and processing, is informed by the textual polarity of the input text, and the textual polarity of candidate evidence passages.

Natural language processing based on textual polarity

A mechanism is provided in a data processing system for using paraphrase metrics for answering questions. The mechanism receives an input question and generating a candidate answer from a corpus of information. The candidate answer has a supporting passage from the corpus of information. The mechanism divides the input question into a first sequence of tokens and divides the supporting passage into a second sequence of tokens. The mechanism identifies a plurality of subsequences of tokens within the second sequence of tokens and applies a paraphrase metric to compare the first sequence of tokens to each of the plurality of subsequences of tokens to generate a plurality of paraphrase metric scores. The mechanism then determines a confidence score for the candidate answer based on a highest paraphrase metric score within the plurality of paraphrase metric scores.

Using paraphrase metrics for answering questions

A method includes obtaining an input text, identifying a first term in the input text, and accessing lexicon data to identify a first entry corresponding to the first term. The first entry includes core data corresponding to domain-independent lexical information for the first term, and non-core data corresponding to domain-specific lexical information for the first term. The method also includes determining that the non-core data of the first entry identifies a second term in the input text as a modifier of the first term. The method further includes generating a partially parsed and bracketed version of the input text. The partially parsed and bracketed version indicates that the second term modifies the first term in the input text. The method also includes generating a parsed version of the input text based on the partially parsed and bracketed version of the input text.

Domain-specific lexically-driven pre-parser

A computer program product including a computer-readable storage medium that has program instructions embodied therewith. The program instructions executable to cause the processor to perform operations including obtaining an input text at a text parser, identifying a first term in the input text, and accessing lexicon data to identify a first entry corresponding to the first term. The first entry includes non-core data that corresponds to domain-specific lexical information for the first term. The operations further include determining that the non-core data identifies a second term in the input text as a modifier of the first term. The operations also include generating a partially parsed and bracketed (PPB) version of the input text. The PPB version indicates that the second term modifies the first term in the input text. The operations further include generating a parsed version of the input text based on the PPB version of the input text.

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

A mechanism is provided in a data processing system for question answering using multi-instance learning. The mechanism trains an answer ranking multi-instance learned model using a ground truth question and answer-key pairs set. When used for answering questions, the mechanism receives an input question from a user and generates one or more candidate answers to the input question. Each of the one or more candidate answers has an associated set of supporting passages. The mechanism determines a confidence value for each of the one or more candidate answers using an answer ranking multi-instance learned model based on the sets of supporting passages. The mechanism ranks the one or more candidate answers by confidence value to form a ranked set of answers, classifies supporting passages to identify the ones which truly support the answer, and presents a final answer from the ranked set of answers, the confidence value for the final answer, and supporting evidence for the final answer to the user.

Multiple instance machine learning for question answering systems

According to an aspect, a candidate token sequence including one or more word tokens is extracted from an unstructured domain glossary that includes entries associated with a domain. A look-up operation is performed to retrieve language data for each word token in the candidate token sequence and annotates each word token in the candidate token sequence found by the look-up operation with corresponding retrieved language data to form an annotated sequence. A pattern match of the annotated sequence is performed relative to a repository of patterns and identifies a best matching pattern from the repository of patterns to the annotated sequence based on matching criteria. The annotated sequence is refined with lexical information associated with the best matching pattern as a refined annotated sequence. The candidate token sequence and the refined annotated sequence are output to a domain-specific computational lexicon file.

Domain-specific computational lexicon formation

Growing community of inventors

Hyde Park, NY, United States of America

Benjamin P Segal