Abstract: Mechanisms are provided in which a first knowledge graph, comprising nodes representing entities and edges between nodes indicative of a relationship between the entities, is received. The mechanisms identify a candidate missing edge connecting a node of the first knowledge graph to another node not present in the first knowledge graph and evaluate the candidate missing edge to determine if the candidate missing edge should be added to the first knowledge graph. The mechanisms expand the first knowledge graph to include the candidate missing edge connecting the node to a newly added node that is newly added to the first knowledge graph, to thereby generate an expanded knowledge graph, in response to the evaluation indicating that the candidate missing edge should be added to the first knowledge graph. The mechanisms then perform an operation on the expanded knowledge graph to generate a knowledge output.

Abstract: A technique for transforming questions for a question answering (QA) system includes clustering received questions by contextual accordance into a question set. A base lexical answer type (LAT) for the question set is determined. LATs of discordant questions in the question set are transformed to the base LAT. Answers for the questions in the question set are aggregated. The aggregated answers are then displayed.

Abstract: Candidate answers are generated by a question-answering system in response to a question from a user. One or more generated candidate answers are compared to previous question-answer sets. The previous question-answer sets are indexed and stored in a database which includes a knowledge graph on the previous questions-answer sets. A previous question-answer set is identified as correlating with a first generated candidate answers. The previous question-answer set is identified using relationships of the database. The first generated candidate answer is restructured using the question as a statement which is embedded with the first generated candidate answer. The restructured generated candidate answer which correlates with the previous question-answer set is supplemented with content from the previous question-answer set.

Abstract: A method, system and a computer program product are provided for classifying elements in a ground truth training set by iteratively assigning machine-annotated training set elements to clusters which are analyzed to identify a prioritized cluster containing one or more elements which are frequently misclassified and display machine-annotated training set elements associated with the first prioritized cluster along with a warning that the first prioritized cluster contains one or more elements which are frequently misclassified to solicit verification or correction feedback from a human subject matter expert (SME) for inclusion in an accepted training set.

Abstract: Mechanisms are provided in which a first knowledge graph, comprising nodes representing entities and edges between nodes indicative of a relationship between the entities, is received. The mechanisms identify a candidate missing edge connecting a node of the first knowledge graph to another node not present in the first knowledge graph and evaluate the candidate missing edge to determine if the candidate missing edge should be added to the first knowledge graph. The mechanisms expand the first knowledge graph to include the candidate missing edge connecting the node to a newly added node that is newly added to the first knowledge graph, to thereby generate an expanded knowledge graph, in response to the evaluation indicating that the candidate missing edge should be added to the first knowledge graph. The mechanisms then perform an operation on the expanded knowledge graph to generate a knowledge output.

Abstract: A method, system and a computer program product are provided for verifying ground truth data by iteratively clustering machine-annotated training set examples with validation set examples to identify and display one or more prioritized review candidate training set examples grouped with validation set examples meeting a predetermined misclassification criteria in order to solicit verification or correction feedback from a human subject matter expert for inclusion in an accepted training set.

Abstract: A method, system and a computer program product are provided for verifying ground truth data by iteratively assigning machine-annotated training set examples to clusters which are prioritized based on verification scores to identify and display one or more prioritized review candidate training set examples grouped in a prioritized cluster in order to solicit verification or correction feedback from a human subject matter expert for inclusion in an accepted training set.

Abstract: Candidate answers are generated by a question-answering system in response to a question from a user. One or more generated candidate answers are compared to previous question-answer sets. The previous question-answer sets are indexed and stored in a database which includes a knowledge graph on the previous questions-answer sets. A previous question-answer set is identified as correlating with a first generated candidate answers. The previous question-answer set is identified using relationships of the database. The first generated candidate answer is restructured using the question as a statement which is embedded with the first generated candidate answer. The restructured generated candidate answer which correlates with the previous question-answer set is supplemented with content from the previous question-answer set.

Abstract: A technique for transforming questions for a question answering (QA) system includes clustering received questions by contextual accordance into a question set. A base lexical answer type (LAT) for the question set is determined. LATs of discordant questions in the question set are transformed to the base LAT. Answers for the questions in the question set are aggregated. The aggregated answers are then displayed.

Abstract: Candidate answers are generated by a question-answering system in response to a question from a user. One or more generated candidate answers are compared to previous question-answer sets. The previous question-answer sets are indexed and stored in a database which includes a knowledge graph on the previous questions-answer sets. A previous question-answer set is identified as correlating with a first generated candidate answers. The previous question-answer set is identified using relationships of the database. The first generated candidate answer is restructured using the question as a statement which is embedded with the first generated candidate answer. The restructured generated candidate answer which correlates with the previous question-answer set is supplemented with content from the previous question-answer set.