Abstract: Automatic removal of AI bias associated with an AI model. A computing device accesses an AI model. The computing device executes two or more independent bias mitigation algorithms, each of the two or more independent bias mitigation algorithms designed to independently remove AI bias from the AI model. Results of execution of the two or more independent bias mitigation algorithms are displayed to the user. A selection is received from the user of one or more bias mitigation algorithms for use with the AI model. The selected one or more bias mitigation algorithms are executed to correct bias in the AI model.

Abstract: The invention is to utilize a process in which synthetic data sets are generated that contain intentional bias to run against an AI model. The purpose is to detect potential bias and if detected, perform bias mitigation procedure on the sensitive attributes associated with the bias. The embodiments are a construction component that constructs an initial artificial intelligence (AI) model using a structured data set with continuous, binary or multi-class prediction labels; a generation component that generates synthetic datasets from the training set wherein protected attributes are simulated; and an execution component that runs the initial model against synthetic biased testing data sets to gage robustness of the initial model by scoring the model and exposing protected attributes to target for bias mitigation.

Abstract: Disclosed is a computer implemented method to identify relevant feedback. The method includes training, with a set of training data, a generative adversarial network (GAN), wherein the GAN includes a generator and a discriminator, and the set of training data is comprised of a plurality of feedback, each instance of feedback includes a value in a plurality of categories, the categories including a positivity value, and a validity value. The method also includes receiving, from a user, a new instance of feedback. The method further includes determining, by the discriminator, a first validity value and a first positivity value of the new instance of feedback. The method includes updating, in response to the first validity value being valid, and the first positivity value being negative, the GAN. The method further includes, displaying the new instance of feedback.

Abstract: A method retrains a cognitive interaction information system. One or more processors monitors an interactive communication between a user and the cognitive interactive information system. The processor(s) identifies an incorrect answer returned by the cognitive interactive information system to a question asked by the user; reevaluates the question utilizing alternative intent classifications to form alternative answers; and presents the alternative answers to the user. The processor(s) receive a selection from the alternative answers from the user; updates processing rules to generate updated processing rules that are based on the selection; and retrains the cognitive interaction information system based on the updated processing rules.

Abstract: In an approach for training data enhancement for an interactive response system, a processor retrieves a set of training data including a set of intents, a set of entities, and a set of utterances that map to each intent. A processor determines iteratively a root verb among the set of utterances for each intent. A processor to determine a set of new intents based on analysis of the determined root verb by performing a pairwise iteration and similarity score over the set of intents. A processor determines iteratively one or more new entities for each new intent. A processor generates a set of new training data based on the set of new intents and entities.

Abstract: In an approach for training data enhancement for an interactive response system, a processor retrieves a set of training data including a set of intents, a set of entities, and a set of utterances that map to each intent. A processor determines iteratively a root verb among the set of utterances for each intent. A processor to determine a set of new intents based on analysis of the determined root verb by performing a pairwise iteration and similarity score over the set of intents. A processor determines iteratively one or more new entities for each new intent. A processor generates a set of new training data based on the set of new intents and entities.

Abstract: Monitoring and instigating shifts in visual focus by monitoring a first duration associated with a first focus point distance, determining that the first focus point distance satisfies a first distance threshold and that the first duration satisfies a first temporal threshold, instigating a change in the first focus point distance, yielding a second focus point distance, wherein the second focus point distance exceeds a second distance threshold, monitoring a second duration associated with the second focus point distance, determining that the second duration satisfies a second temporal threshold, and providing an output indicating satisfaction of the second distance threshold and second temporal threshold.

Abstract: A set of documents is received for processing and extraction. A set of processing engines is received, and each processing engine has an expected benefit when processing a document with associated document metadata. The set of documents is analyzed to determine document metadata to be associated with the document. An expected benefit is determined for each of the documents of the set of document when the respective document is processed by a respective processing engine in the set processing engines. An expected cost for processing is determined for each of the documents in each of the set of processing engines. A processing plan for the set of documents is determined wherein the processing plan identifies a selection of documents to be run in respective processing engines of the set of processing engines based on a cost versus benefit analysis. The processing plan is executed extracting information from the identified selection of documents.

Abstract: An information processing system comprises one or more processing platforms and implements a centralized storage provisioning and management system and a plurality of service provider storage systems coupled to the centralized storage provisioning and management system. The centralized storage provisioning and management system is configured to control provisioning and management of the service provider storage systems utilizing information collected from the service provider storage systems. The service provider storage systems may comprise respective service provider data centers, and the centralized storage provisioning and management system may comprise an additional data center separate from the service provider data centers. The centralized storage provisioning and management system may comprise a centralized control path implemented apart from the service provider storage systems.

Abstract: Disclosed is a computer implemented method to identify relevant feedback. The method includes training, with a set of training data, a generative adversarial network (GAN), wherein the GAN includes a generator and a discriminator, and the set of training data is comprised of a plurality of feedback, each instance of feedback includes a value in a plurality of categories, the categories including a positivity value, and a validity value. The method also includes receiving, from a user, a new instance of feedback. The method further includes determining, by the discriminator, a first validity value and a first positivity value of the new instance of feedback. The method includes updating, in response to the first validity value being valid, and the first positivity value being negative, the GAN. The method further includes, displaying the new instance of feedback.

Abstract: A set of documents is received for processing and extraction. A set of processing engines is received, and each processing engine has an expected benefit when processing a document with associated document metadata. The set of documents is analyzed to determine document metadata to be associated with the document. An expected benefit is determined for each of the documents of the set of document when the respective document is processed by a respective processing engine in the set processing engines. An expected cost for processing is determined for each of the documents in each of the set of processing engines. A processing plan for the set of documents is determined wherein the processing plan identifies a selection of documents to be run in respective processing engines of the set of processing engines based on a cost versus benefit analysis. The processing plan is executed extracting information from the identified selection of documents.

Abstract: A method retrains a cognitive interaction information system. One or more processors monitors an interactive communication between a user and the cognitive interactive information system. The processor(s) identifies an incorrect answer returned by the cognitive interactive information system to a question asked by the user; reevaluates the question utilizing alternative intent classifications to form alternative answers; and presents the alternative answers to the user. The processor(s) receive a selection from the alternative answers from the user; updates processing rules to generate updated processing rules that are based on the selection; and retrains the cognitive interaction information system based on the updated processing rules.

Abstract: A method improves a functionality of a conversational agent that is generated by an artificial intelligence (AI) system. A conversational agent receives a first utterance from a first entity. The AI system identifies an unverified response to the first utterance; sends the unverified response to the first entity; and receives a positive feedback indication about the unverified response from the first entity. The AI system searches a data store in order to identify an entry for a second utterance by a second entity, where the second entity has sent a positive feedback for the unverified response. The AI system sends the second utterance and the unverified response to the first entity, and receives a positive feedback for the unverified response to the second utterance from the first entity in order to mark the unverified response as a verified response, which responds to future receipts of the first utterance.

Abstract: A method, computer system, and computer program product for chat protection. The embodiment may include receiving, in a chat session, a user-spoken communication and one or more inputs specific to a software program. The embodiment may also include predicting a next communication by the user based on the received user spoken communication and the one or more inputs. The embodiment may further include, in response to the predicted next communication containing untoward content, performing a remedial action.

Abstract: A method, computer system, and computer program product for chat protection. The embodiment may include receiving, in a chat session, a user-spoken communication and one or more inputs specific to a software program. The embodiment may also include predicting a next communication by the user based on the received user spoken communication and the one or more inputs. The embodiment may further include, in response to the predicted next communication containing untoward content, performing a remedial action.

Abstract: A method improves a functionality of a conversational agent that is generated by an artificial intelligence (AI) system. A conversational agent receives a first utterance from a first entity. The AI system identifies an unverified response to the first utterance; sends the unverified response to the first entity; and receives a positive feedback indication about the unverified response from the first entity. The AI system searches a data store in order to identify an entry for a second utterance by a second entity, where the second entity has sent a positive feedback for the unverified response. The AI system sends the second utterance and the unverified response to the first entity, and receives a positive feedback for the unverified response to the second utterance from the first entity in order to mark the unverified response as a verified response, which responds to future receipts of the first utterance.

Abstract: An information processing system comprises a centralized database and at least one processing device implementing a selection algorithm for automated provisioning and management of a plurality of storage arrays based on information collected from the storage arrays and stored in the centralized database. The information stored in the centralized database may comprise at least one of storage utilization, performance, network bandwidth and end of service for each of the storage arrays. The selection algorithm is configured to determine optimal placement of data across the storage arrays based on the information stored in the centralized database. For example, the selection algorithm may be configured to determine one or more locations within the plurality of storage arrays to allocate as new storage responsive to a provisioning request.