Abstract: A first list that includes a first set of one or more concept terms may be obtained. The first set of one or more concept terms may be candidates for being conceptually related to a seed concept term. Prior to the obtaining, a first client computing device may provide a first plurality of individual characters and the seed concept term to a first user using the first client computing device. The first client computing device may prompt the first user to generate the first set of one or more concept terms that are conceptually related to the seed concept term using one or more of the first plurality of individual characters. In response to the obtaining, one or more particular categories to which each of the first set of one or more concept terms belongs to may be determined.

Abstract: For automatic operation of an ergonomic equipment according to dynamic workplace conditions, an activity being performed in a workplace by a person at a first time is determined based on an input from a data processing system. A group is selected corresponding to the activity. An ergonomic policy is modified to form a modified ergonomic policy. The ergonomic policy applies to the activity, and the modification is based on a condition existing in the workplace at the first time of the person performing the activity. Independent of a participation of the person, and when the person is not in compliance with the modified ergonomic policy, an ergonomic control is activated. The ergonomic control causes a change in an ergonomic feature of the ergonomic equipment, the change causing the person to become compliant with the modified ergonomic policy.

Abstract: For automatic operation of an ergonomic equipment according to dynamic workplace conditions, an activity being performed in a workplace by a person at a first time is determined based on an input from a data processing system. A group is selected corresponding to the activity. An ergonomic policy is modified to form a modified ergonomic policy. The ergonomic policy applies to the activity, and the modification is based on a condition existing in the workplace at the first time of the person performing the activity. Independent of a participation of the person, and when the person is not in compliance with the modified ergonomic policy, an ergonomic control is activated. The ergonomic control causes a change in an ergonomic feature of the ergonomic equipment, the change causing the person to become compliant with the modified ergonomic policy.

Abstract: A method, apparatus, system and a computer program product are provided for scoring performance of a chatbot by capturing specified node performance metrics based on user interactions with one or more nodes in a dialog flow for the chatbot; assigning a score to each of the one or more nodes based on the specified node performance metrics; and assessing a performance measure for at least a portion of the chatbot by combining scores assigned to selected nodes in the dialog flow.

Abstract: A computer-implemented method according to one embodiment includes identifying a plurality of different summaries for a single instance of content, calculating a relevancy score for each of the plurality of different summaries, and selecting one of the plurality of different summaries, based on the relevancy score for each of the plurality of different summaries.

Abstract: A system and a computer program product are provided for evaluating question-answer pairs in an answer key by comparing a first answer key answer to a plurality of candidate answers to determine if the answer key may have a problem if the plurality of candidate answers are more similar to one another than to the first answer and to determine if the plurality of candidate answers has gradient information which may be used to update the answer key if not already included in the answer key.

Abstract: Embodiments include method, systems and computer program products for coaching an individual during an interaction with a client to produce a desired outcome. Aspects include receiving a user profile for the client, one or more needs of the client, and a goal of the interaction and receiving a modeling profile for the client and relevant environmental information for the client. Aspects also include monitoring the interaction between the individual and the client and analyzing a feedback of the client to actions of the individual and providing guidance to the individual to assist the individual in producing the desired outcome, wherein the guidance is based on the feedback.

Abstract: A method for training a question answering system includes providing training questions to a question answering system executing on a computer and to a plurality of subject matter experts. The question answering system generates first answers to each training question. Second answers to the training questions are received from the subject matter experts. Feature scores for each of the first answers and the second answers are generated and compared across the second answers and the first answers. Each of the feature scores is representative of a quality of an answer that is indicative of relevance to a corresponding training question. Based on the comparing, a measure of consistency of the feature scores of the second answers is determined, and a measure of consistency of the feature scores of the second answers to the first answers is determined. The measures of consistency are transmitted to the subject matter experts.

Abstract: A method for ground truth generation includes providing training questions to a machine learning system executing on a computer. The machine learning system generates candidate answers to each of the training questions. The method also includes providing the candidate answers to a plurality of subject matter experts for evaluation with respect to the training questions, wherein the evaluation comprises assignment of an SME relevance score to each of the candidate answers. The method further includes analyzing each of the candidate answers with respect to a plurality of scoring features, wherein each of the scoring features is indicative of quality of the candidate answer. The method yet further includes generating a ground truth metric value that indicates a measure of agreement between the subject matter experts relative to a measure of agreement between results of the analyzing.

Abstract: A computer-implemented method according to one embodiment includes identifying a summary of a single instance of content, monitoring user interaction with the summary, and determining a relevancy of the summary to the single instance of content, based on the user interaction.

Abstract: According to one exemplary embodiment, a method for dynamically defining topics from content objects used to answer a question in a question answering system is provided. The method may include receiving the content objects. The method may include identifying the topics within the received content objects. The method may include generating a graph based on the identified plurality of topics, whereby nodes map to the topics. The method may include calculating edge weights associated with each edge based on semantic relations associated with the topics. The method may include determining if the calculated edge weight associated an edge exceeds a threshold value. The method may include generating a combination topic based on determining that the edge weight associated with the edge exceeds the threshold value.

Abstract: An approach is provided that analyzes electronic document sets, each of the sets written by a different author. The analysis includes performing a normalized sentiment analysis of the documents which results in normalized sentiment scores that pertain to each of the authors. The normalize sentiment scores are stored in a data store that is accessible from a question answering (QA) system. The question answering system then receives a sentiment-based question. Responsively, the QA system generates a qualitative set of candidate answers, with the candidate answers based at least in part on the normalized sentiment scores retrieved from the data store.

Abstract: A method, system and a computer program product are provided for interactively adjusting completion option suggestions based on user actions in a word processing application, such as a messaging application, by monitoring user interactions to detect one or more non-selected suggestions from a displayed first set of completion option suggestions for completing a first user message input, reprioritizing the one or more non-selected suggestions to reflect a reduced probability that the one or more non-selected suggestions will be selected by the user, and displaying a second set of one or more completion option suggestions for completing a second user message input, where the second set of one or more completion option suggestions is identified at least in part based on the reprioritized one or more non-selected suggestions.

Abstract: An approach is provided in which an information handling system performs multiple tests using a cognitive service and multiple trained machine learning models on user data corresponding to a user application. For each of the multiple tests, a different one of the trained machine learning models is utilized. The information handling system generates results from the tests and then selects at least one of the trained machine learning models based on the test results. In turn, the information handling system assigns the cognitive service and the selected trained machine learning models to the user application.

Abstract: According to one exemplary embodiment, a method for dynamically defining topics from content objects used to answer a question in a question answering system is provided. The method may include receiving the content objects. The method may include identifying the topics within the received content objects. The method may include generating a graph based on the identified plurality of topics, whereby nodes map to the topics. The method may include calculating edge weights associated with each edge based on semantic relations associated with the topics. The method may include determining if the calculated edge weight associated an edge exceeds a threshold value. The method may include generating a combination topic based on determining that the edge weight associated with the edge exceeds the threshold value.

Abstract: A method, apparatus, system and a computer program product are provided for scoring performance of a chatbot by capturing specified node performance metrics based on user interactions with one or more nodes in a dialog flow for the chatbot; assigning a score to each of the one or more nodes based on the specified node performance metrics; and assessing a performance measure for at least a portion of the chatbot by combining scores assigned to selected nodes in the dialog flow.

Abstract: An approach is provided that analyzes electronic document sets, each of the sets written by a different author. The analysis includes performing a normalized sentiment analysis of the documents which results in normalized sentiment scores that pertain to each of the authors. The normalize sentiment scores are stored in a data store that is accessible from a question answering (QA) system. The question answering system then receives a sentiment-based question. Responsively, the QA system generates a qualitative set of candidate answers, with the candidate answers based at least in part on the normalized sentiment scores retrieved from the data store.

Abstract: Clustering a set of natural language queries NLQs based on a set of significant events retrieved from a corpus stored in a computer system is described. A set of NLQs is used by a search engine for searching a selected corpus to retrieve respective sets of significant events. The set of NLQs is clustered into a plurality of NLQ clusters according to a threshold number of common significant events being returned by the search engine for respective members of an NLQ cluster.

Abstract: Clustering a set of natural language queries NLQs based on a set of significant events retrieved from a corpus stored in a computer system is described. A set of NLQs is used by a search engine for searching a selected corpus to retrieve respective sets of significant events. The set of NLQs is clustered into a plurality of NLQ clusters according to a number of common significant events being returned by the search engine for respective members of an NLQ cluster.

Abstract: A knowledge graph is built based on a corpus stored in the computer system. The corpus includes a set of events and each event includes a respective set of entities. A first set of entities is identified in the NLQ. The first set of entities is used to identify a first set of significant events in the selected corpus in a first search depth. A second set of entities is identified in the first set of significant events. The knowledge graph determines which ones of the second set of entities are related to the entities in the first set of entities to produce a filtered second set of entities. The filtered second set of entities is used to identify a second set of significant events in the selected corpus in a second search depth. Members of the first and second set of significant events are presented to a user.