International Business Machines Corporation

Globalfoundries Inc.

Sugato Bagchi

David Angelo Ferrucci

Anthony Tom Levas

James J Fan

Erik Thomas Mueller

Aditya Anand Kalyanpur

Christopher A Welty

Wlodek Wlodzimierz Zadrozny

Kenneth James Barker

Mihaela Ancuta Bornea

Soumyadip Ghosh

David C Gondek

Michael A Barborak

Jayant R Kalagnanam

Alfio Massimiliano Gliozzo

James W Murdock, Iv

Jennifer Chu-Carroll

John Martin Prager

Stacey C Ramos

Sarthak Dash

Laura Wynter

Branimir Konstantinov Boguraev

Siddharth A Patwardhan

Sara Rosenthal

Nandana Sampath Mihindukulasooriya

Ching-Hua Chen-Ritzo

Adam R Faulkner

Steven D Daniels

William A Tulskie, Jr

Joseph Anthony Morrone

Wendy Dawn Cornell

Jeffrey Kurt Weber

Lindsay E Burns

Yanpeng Li

Steven C Catlett

Xue Bai

A system and method for structure-based, small molecule activity prediction using binding mode prediction information. Binding scores between ligands and target molecules, (e.g. proteins, RNA, DNA, lipids, sugars) are first generated using molecular docking. A first machine learned deep neural network (DNN) model is developed using data representing the molecular ligand-target pair 3D structures and docking features to predict binding modes. Using transfer learning, weights of layers learned in the first machine learned model are used as weights in layers of a second machine learned DNN model used to more accurately improve the performance of activity prediction of the second machine learned model. For a target newly paired ligand-target complex, the method further implements a binding mode selector for selecting one or more particular binding poses for input to the activity prediction model for use in activity mode prediction of an activity of the target paired ligand-protein complex.

Structure-based, ligand activity prediction using binding mode prediction information

An embodiment for encoding permutation-invariant representations of linearized tabular data. The embodiment may receive input including tabular data and linearize a column or row within the received tabular data. The embodiment may automatically assign an increasing sequence of position identifiers to each non-delimiting tokenized cell in the linearized column or row until a header delimiter is reached. The embodiment may, in response to reaching the header delimiter, automatically assign a monotonically increasing sequence of position identifiers for each non-delimiting tokenized cell positioned after the header delimiter, restarting from an integer corresponding to 1 greater than the position identifier assigned to the header delimiter for each non-delimiting tokenized cell positioned after cell delimiters. The embodiment may automatically assign a static position identifier for each of the cell delimiters in the linearized column or row and output an encoded permutation-invariant representation of the linearized column or row.

Permutation invariance for representing linearized tabular data

An embodiment for improved linking of tabular columns to column types in an ontology unseen during training. The embodiment may for a target table, encode a target tabular query column, table headers, and target types independently to generate permutation invariant representations of tabular data associated with the target table. The embodiment may, for each of the target types, extract and further encode auxiliary information. The embodiment may process the encoded tabular data to obtain a first vector and a second vector. The embodiment may concatenate the first vector and the second vector to generate a final query vector. The embodiment may process the encoded target types through a third transformer to obtain a third vector. The embodiment may calculate a score to model interactions between the target tabular query column of the target table and the target types.

Linking tabular columns to unseen ontologies

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 mechanism is provided in a data processing system for exploring knowledge. The mechanism receives a set of known facts. The mechanism traverses paths in an ontology for a domain of knowledge from known facts in the set of known facts to one or more hypotheses. The ontology includes a plurality of entity types and a plurality of relationships between the entity types. The mechanism presents one or more hypotheses to a user.

Leveraging an external ontology for graph expansion in inference systems

Provided herein are techniques for processing a context-situated inquiry to provide results satisfying the inquiry. An inquiry and its supporting context are processed using natural language processing to determine an interpretation for the inquiry and context, and the interpretation is presented to receive corrective information for the interpretation. The corrective information is applied to the interpretation and content is retrieved based on the interpretation of inquiry and context to produce candidate results for the inquiry. Supplemental information is iteratively received to generate updated candidate results.

Processing context-based inquiries for knowledge retrieval

A decision-support system for medical diagnosis and treatment comprises software modules embodied on a computer readable medium, and the software modules comprise an input/output module and a question-answering module. The method receives patient case information using the input/output module, and generates a medical diagnosis or treatment query based on the patient case information and also generates a plurality of medical diagnosis or treatment answers for the query using the question-answering module. The method also calculates numerical values for multiple medical evidence dimensions from medical evidence sources for each of the answers using the question-answering module and also calculates a corresponding confidence value for each of the answers based on the numerical value of each evidence dimension using the question-answering module. The method further outputs the medical diagnosis or treatment answers, the corresponding confidence values, and the numerical values of each medical evidence dimension for one or more selected medical diagnosis or treatment answers using the input/output module.

A system and method for automatically mapping LATs and candidate answers to multiple taxonomies without a need to merge these taxonomies. The method includes using a syntactic analysis of a corpus to extract all type instances of the LAT. The extracted instances are then mapped to a given taxonomy and clustered in a set of supertypes. Each supertype receives a score based on the coverage of LAT instances in the corpus. The method includes mapping the candidate answer to the same taxonomy to determine if the candidate answer is an instance of a significant supertype. Then the score of a candidate answer is obtained by aggregating or taking a maximum of the score of the matched significant supertypes. This score evaluates the type match between the LAT and candidate answer for a taxonomy. Multiple taxonomies can be used to increase the chance of LAT and candidate answer mapping.

Type evaluation in a question-answering system

In a method of answering questions, a question is received, a question LAT is determined, and a candidate answer to the question is identified. Preliminary types for the candidate answer are determined using first components to produce the preliminary types. Each of the first components produces a preliminary type using different methods. A first type-score representing a degree of match between the preliminary type and the question LAT is produced. Each preliminary type and each first type-score is evaluated using second components. Each of the second components produces a second score based on a combination of the first type-score and a measure of degree that the preliminary type matches the question LAT. The second components use different methods to produce the second score. A final score representing a degree of confidence that the candidate answer matches the question LAT is calculated based on the second score.

Combining different type coercion components for deferred type evaluation

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 business process modeling framework is used for data quality analysis. The modeling framework represents the sources of transactions entering the information processing system, the various tasks within the process that manipulate or transform these transactions, and the data repositories in which the transactions are stored or aggregated. A subset of these tasks is associated as the potential error introduction sources, and the rate and magnitude of various error classes at each such task are probabilistically modeled. This model can be used to predict how changes in transactions volumes and business processes impact data quality at the aggregate level in the data repositories. The model can also account for the presence of error correcting controls and assess how the placement and effectiveness of these controls alter the propagation and aggregation of errors. Optimization techniques are used for the placement of error correcting controls that meet target quality requirements while minimizing the cost of operating these controls. This analysis also contributes to the development of business 'dashboards' that allow decision-makers to monitor and react to key performance indicators (KPIs) based on aggregation of the transactions being processed. Data quality estimation in real time provides the accuracy of these KPIs (in terms of the probability that a KPI is above or below a given value), which may condition the action undertaken by the decision-maker.

Data quality management using business process modeling

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.

In a method of answering questions and scoring answers, a title and at least one topical field are identified for a document. A field name and field content associated with the topical field is identified, and a title-oriented document is created by combining the title, the field name, and the field content associated with the topical field. For each title-oriented document, a term in the title is matched to previously established categories to produce a title concept identifier. The topical field is synthesized to produce a field concept identifier and a field content concept identifier. A question is received. The question topic term and the question content identifier are used to identify at least one question-matching relation instance. The title concept identifier of each question-matching relation instance is identified as a candidate answer to the question. Each candidate answer and a corresponding answer score is output.

Growing community of inventors

White Plains, NY, United States of America

Sugato Bagchi