Abstract: Curation of a corpus of a cognitive computing system is performed by reporting to a user a cluster model of a parse tree structure of discrepancies and corresponding assigned confidence factors detected between at least a portion of a first electronic document and a second or more electronic documents in the information corpus. Responsive to a selection by the user of a discrepancy cluster model, drill-down details regarding the discrepancy are returned to the user, for subsequent user selection of an administrative action option for handling the detected discrepancy to curate the information corpus.

Abstract: A technique for instance-specific feature-based cross-document sentiment aggregation includes analyzing input data to determine an entity referenced in the input data. One or more salient features of the entity are identified. Multiple documents that reference the entity are located. The salient features in each of the multiple documents are identified. Respective sentiment values are assigned to each of the salient features identified in the multiple documents. Respective sub-graphs are created for each of the multiple documents. The sub-graphs specify the sentiment values assigned to each of the salient features identified in an associated one of the multiple documents. The assigned sentiment values for each of the salient features are aggregated based on the sub-graphs. Finally, output data that is associated with the input data is generated. The output data provides an indication of the aggregated sentiment value for each of the salient features.

Abstract: According to an embodiment of the present invention, a system analyzes a collection of medical documents to identify within document content risk factors of medical conditions associated with corresponding activities. A processor in the system maps the identified risk factors of the activities to one or more medical tests for the associated medical conditions, and analyzes a medical record and social media communications of a patient to determine participation of the patient in one or more of the corresponding activities. The processor determines the one or more medical tests to conduct from the mapping based on the risk factors associated with the determined activities of the patient. Embodiments of the present invention further include a method and computer program product for analyzing patient activity to conduct appropriate medical tests in substantially the same manner described above.

Abstract: A user session for a client device may be initiated by a computerized answering system. Answers to one or more questions may be provided via a network for presentation in a user interface of a display of the client device, where the presentation of the answers may be based on a default profile. User interaction with one or more of the answers presented in the user interface of the display of the client device is monitored during the user session. A first user profile is selected from a plurality of user profiles in response to determining attributes of the user interaction correspond to attributes of the first user profile. The user interface of the display of the client device is modified to change from presenting the answers based on the default profile to presenting the answers based on the first user profile.

Abstract: A selected document from corpus of a cognitive computing system is processed according to its association with a category of documents already contained within the corpus, such as a topical category. Then, the cognitive computing system is engaged automatically to query one or more questions previously-associated with the category to discover discrepancies between the selected document and the other corpus documents. If a discrepancy is found, a confidence factor based upon extracted natural language entities and relationships is assigned to the discrepancy, and it is flagged and reported to a user for reconciliation.

Abstract: Performing an operation comprising applying one or more natural language processing (NLP) algorithms to a text transcription of a medical encounter dialogue to determine a plurality of features of the dialogue, processing, by a machine learning (ML) model executing on a processor, the text transcription and the plurality of features of the dialogue to identify a plurality of candidate medications from a knowledge base corresponding to a first statement made by a medical professional during the medical encounter, and outputting an indication of the plurality of candidate medications for display.

Abstract: A new document is processed for ingestion into a corpus of a cognitive computing system by associating with a category of documents already contained within the corpus, such as a topical category. Then, the cognitive computing system is engaged automatically to query one or more questions previously-associated with the category to discover discrepancies between the new document and those already in the corpus. If a discrepancy is found, a confidence factor based upon extracted natural language entities and relationships is assigned to the discrepancy, and it is flagged and reported to a user for reconciliation.

Abstract: Aspects include generation of automated response follow-up. A response to a question from a user is received at a response follow-up system. The response follow-up system analyzes the response using natural language processing to identify one or more response terms. The response follow-up system generates one or more follow-up questions based on the one or more response terms. Based on the response, one or more follow-up responses to the one or more follow-up questions are pre-fetched from one or more content provider systems including one or more content servers, where a question answering system including the response follow-up system is communicatively coupled to the one or more content provider systems through a network. The response follow-up system modifies an aspect of a user interface displayed to the user based on the one or more follow-up questions and the one or more follow-up responses.

Abstract: Software that answers questions asked of question answering systems, by performing the following steps: (i) identifying a hierarchy of question and answer pairs, where a first answer paired to a first question in the hierarchy of question and answer pairs includes at least a second answer paired to a second question in the hierarchy of question and answer pairs; (ii) receiving, by a question answering system, an input question from a first user; (iii) identifying first user contextual information pertaining to the first user; and (iv) answering the input question, by the question answering system, based, at least in part, on the hierarchy of question and answer pairs and the first user contextual information.

Abstract: A mechanism is provided in a data processing system for automatically generating question and answer pairs for training a question answering system for a given domain. The mechanism receives user input of question text for a question to be submitted to a question answering system in a user interface. The mechanism determines a question strength score for the question text. The question strength score represents a likelihood the question text will result in a correct answer with high confidence. The mechanism presents a graphical representation of the question strength score in the user interface.

Abstract: A mechanism is provided in a data processing system for identifying and resolving issues in a distributed infrastructure. A log error processor monitors error logs of a plurality of data processing nodes within the distributed infrastructure. In response to the log error processor detecting an error in a given node within the distributed infrastructure, the log error processor provides error data for the error to the machine learning model and receiving from the machine learning model a set of potential solutions and associated confidence values. An operation extraction component extracts from each potential solution in the set of potential solutions a set of operations to resolve the error. A classifier component maps each set of operations to a set of executable operations that are executable by the given node. A solution scorer component determines whether to perform automatic resolution using a selected potential solution and its corresponding set of executable operations.

Abstract: A domain specific ontology collection associated with a user is determined. At least one action of the user is received. A task for the user is determined based on the domain specific ontology collection for the user and the at least one action of the user.

Abstract: Aspects include engaging a user in a chat flow by a dialog system. A user sentiment associated with a system response provided by the dialog system as part of the chat flow is determined based on observation of the user. A next system response is rerouted from a planned sequence of the chat flow to a sentiment-based repair sequence to alter content delivered to the user based on a detected aspect of the user sentiment.

Abstract: Curation of a corpus of a cognitive computing system is performed by reporting to a user a cluster model of a parse tree structure of discrepancies and corresponding assigned confidence factors detected between at least a portion of a first electronic document and a second or more electronic documents in the information corpus. Responsive to a selection by the user of a discrepancy cluster model, drill-down details regarding the discrepancy are returned to the user, for subsequent user selection of an administrative action option for handling the detected discrepancy to curate the information corpus.

Abstract: Curation of a corpus of a cognitive computing system is performed interactively by reporting on user interface device to a user a parse tree illustration of discrepancies and corresponding assigned confidence factors detected between at least a portion of a first document and a second or more documents in the corpus. Responsive to a user selection of an illustrated discrepancy in the parse tree, a drill-down dialog is prepared and displayed which shows at least a text string for the portion of the first document and at least one conflicting text string from the second or more documents, and which provides at least one user-selectable administrative action option for handling the detected discrepancy. Responsive to receipt of user selection of an administrative action option, the computing system performs the action to handle the detected discrepancy.

Abstract: A mechanism is provided in a question answering system for categorizing questions. The mechanism clusters documents from a corpus of documents to form a nested structure of clusters of documents. The mechanism records questions answered by question answering system in a database in association with answers returned and answer confidence values. The mechanism maps the questions to the nested structure of clusters of documents to form a nested structure of clusters of questions. The mechanism presents recommended questions based on the nested structure of clusters of questions in a user interface of the question answering system.

Abstract: Aspects include cross validation of user feedback in a dialog system. A repository of previous user feedback associated with a user interface is accessed. One or more identified features in the previous user feedback are classified. A sequence of cross-validation questions is generated in a dialog system to elicit further feedback from a current user of the user interface based on the one or more identified features and observed interactions of the current user with the user interface. Responses to the sequence of cross-validation questions are filtered to group the further feedback associated with the one or more identified features. One or more change suggestions to modify the user interface are stored based on the previous user feedback and the further feedback associated with the one or more identified features.

Abstract: Performing an operation comprising applying one or more natural language processing (NLP) algorithms to a text transcription of a medical encounter dialogue to determine a plurality of features of the dialogue, processing, by a machine learning (ML) model executing on a processor, the text transcription and the plurality of features of the dialogue to identify a plurality of candidate medications from a knowledge base corresponding to a first statement made by a medical professional during the medical encounter, and outputting an indication of the plurality of candidate medications for display.

Abstract: A mechanism is provided in a data processing system for identifying and resolving issues in a distributed infrastructure. A log error processor monitors error logs of a plurality of data processing nodes within the distributed infrastructure. In response to the log error processor detecting an error in a given node within the distributed infrastructure, the log error processor provides error data for the error to the machine learning model and receiving from the machine learning model a set of potential solutions and associated confidence values. An operation extraction component extracts from each potential solution in the set of potential solutions a set of operations to resolve the error. A classifier component maps each set of operations to a set of executable operations that are executable by the given node. A solution scorer component determines whether to perform automatic resolution using a selected potential solution and its corresponding set of executable operations.

Abstract: A selected document from corpus of a cognitive computing system is processed according to its association with a category of documents already contained within the corpus, such as a topical category. Then, the cognitive computing system is engaged automatically to query one or more questions previously-associated with the category to discover discrepancies between the selected document and the other corpus documents. If a discrepancy is found, a confidence factor based upon extracted natural language entities and relationships is assigned to the discrepancy, and it is flagged and reported to a user for reconciliation.