International Business Machines Corporation

Thomas P Pitzen

Michael Britt

Richard Joseph Stevens

Adam Charles Lange-Pearson

Douglas Earl Hays

Michael Peter Etgen

Christopher Thomas Gloe

Chris M Mwarabu

Methods to provide selective supporting evidence processing by applying a first machine learning (ML) model to a first candidate answer to generate a first confidence score that does not consider supporting evidence for the first candidate answer, determining, from a second ML model, an expected contribution of processing supporting evidence for the first candidate answer, and upon determining that the expected contribution does not exceed a specified threshold, skipping supporting evidence processing for the first candidate answer.

Avoiding supporting evidence processing when evidence scoring does not affect final ranking of a candidate answer

Systems and computer program products to provide selective supporting evidence processing by applying a first machine learning (ML) model to a first candidate answer to generate a first confidence score that does not consider supporting evidence for the first candidate answer, determining, from a second ML model, an expected contribution of processing supporting evidence for the first candidate answer, and upon determining that the expected contribution does not exceed a specified threshold, skipping supporting evidence processing for the first candidate answer.

Systems, methods, and computer program products to perform an operation comprising receiving a case, generating a set of candidate answers for the case, excluding a first candidate answer from the set of candidate answers upon determining that a first attribute in the case precludes returning the first candidate answer as a valid response to the case, and processing supporting evidence for the remaining candidate answers in the set of candidate answers.

Avoidance of supporting evidence processing based on key attribute predictors

Systems, methods, and computer program products to perform an operation comprising receiving a case from a user, determining a level of sophistication of the user, determining a level of sophistication associated with each of a plurality of items of supporting evidence in a corpus of information, selecting a subset of the plurality of items of supporting evidence based on the determined levels of sophistication, and returning the selected subset to the user as part of a response to the case.

Tailored supporting evidence

In an embodiment, a guest operating system receives first host network information that identifies a host virtual network adapter. The first host network information uniquely identifies the host virtual network adapter. The guest operating system sends a first frame that comprises the first host network information to a guest virtual network adapter. The guest virtual network adapter sends the first frame to the host virtual network adapter. The guest operating system receives second host network information that identifies the host virtual network adapter. The second host network information uniquely identifies the host virtual network adapter. The guest operating system sends a second frame that comprises the second host network information to the guest virtual network adapter. The guest virtual network adapter sends the second frame to the host virtual network adapter identified by the second host network information in the second frame.

Communication between a host operating system and a guest operating system

A method, apparatus, and computer usable code to grant access to a scripted code hosted at a host site wherein the host site has a window read-only property. A computer client receives a key-code. The computer client determines if key-code matches a known correct window-returning code. Based on that, the computer invokes the key-code to obtain a read-only property of the key-code and determines if the read-only property matches the known correct window read-only property. Invoking means treating the key-code as a computer instruction and executing the computer instruction. The computer may grant access based on a determination that the read-only property matches.

Authenticating a source of a scripted code

A method, data processing system, and computer usable code are provided for generating content dynamically without a Web server. Responsive to a request to display a document containing markup language content on a client data processing system, a determination is made as to whether a utility script is present in the document. A utility application associated with the utility script is loaded on the client data processing system, if the utility script is present. Then, the utility application processes the utility script to dynamically generate dynamic content for display with markup language content.

Growing community of inventors

Rochester, MN, United States of America

Thomas P Pitzen