Abstract: Mechanisms, in a Question and Answer (QA) system comprising a processor and a memory are provided for generating an answer to a question. A question is received for which an answer is sought as part of a communication exchange. The question is processed to generate candidate answers and corresponding confidence scores and perform a context based selection of a final answer from the candidate answers. The selected final answer is output as a final answer to the question via a computing device. The context based selection involves determining a context of the input question and selecting a final answer from the one or more candidate answers based on the context of the input question. The selected final answer is an answer previously provided in association with the context of the question.

Abstract: An optimal visualization format for a data corpus is automatically selected and generated based upon a natural language query or statement about the data corpus from a user by accessing the subject data corpus; receiving the query or statement from the user a natural language expression; identifying symbols in the query or statement through natural language processing; mapping the symbols to weights for a plurality of visualization formats; scoring the visualization formats; and generating a visualization of the subject data corpus according to the scores. Optional metadata, such as row and column labels, database field labels, and XML DTD's may be mined for symbols, as well. The new tool may generate the visualization as a digital image file, a digital document file, a digital movie file, a digital three-dimensional model file, or a combination of these.

Abstract: Deep semantic analysis is performed on an electronic literary work in order to detect plot elements and optional other storyline elements such as characters within the work. Multiple levels of abstract are generated into a model representing the literary work, wherein each element in each abstraction level may be independently rated for preference by a user. Through comparison of multiple abstraction models and one or more user rating preferences, one or more alternative literary works may be automatically recommended to the user.

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: 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 mechanism is provided in a computing device configured with instructions executing on a processor of the computing device to implement a ground truth generation system for quality assessment scoring of articles in a corpus. The ground truth generation system receives recommendations of a set of recommended articles from subject matter experts. The ground truth generation system identifies a set of non-recommended articles. A topic clustering component within the ground truth generation system performs topic clustering on a combination of the set of recommended articles and the set of non-recommended articles to form a set of topic clusters containing recommended articles and non-recommended articles. The ground truth generation system identifies a first number of recommended articles and a second number of non-recommended articles in each of the set of topic clusters to form a quality assessment training set.

Abstract: A search engine is enhanced to employ user preferences to customize answer output by, receiving a first plurality of candidate answers and weights to a first search query for a first user from a first stage of a non-semantic search engine routing and processing path; augmenting the weights for the plurality of candidate answers according to a set of preference coefficients according to a first set of preferences for the first user; selecting one or more of the first plurality of candidate answers according to the augmented weights; and producing an output including the selected one or more candidate answers.

Abstract: A technique for dynamic augmented reality media creation includes an analysis of reality content received by a device. Augmentation data is identified based on the analysis of the reality content, and then the augmentation data is displayed to the user via the device. A capture module determines whether the reality content meets capture event criteria and, if the criteria is met, augmented reality content is created and captured prior to a display of the augmentation data to the user.

Abstract: A technique for dynamic augmented reality media creation includes an analysis of reality content received by a device. Augmentation data is identified based on the analysis of the reality content, and then the augmentation data is displayed to the user via the device. A capture module determines whether the reality content meets capture event criteria and, if the criteria is met, augmented reality content is created and captured prior to a display of the augmentation data to the user.

Abstract: A classifier receives a document from a multi-document transaction. The classifier analyzes the document to identify one or more embedded dates in the content of the document and context of one or more positions of the one or more embedded dates in the document. The classifier evaluates each of the one or more embedded dates based on the separate context of each of the one or more positions within the document and a relative age of the one or more embedded dates in view of temporal characteristics of multiple categories of documents of a transaction to select a particular category associated with the document from among the multiple categories. The classifier classifies the document within the transaction as a particular logical type identified by the particular category from among multiple logical types.

Abstract: An approach is described for adjusting prominence of a participant profile in a social networking interface. An associated method may include receiving an activity stream update of the participant and calculating a relevancy score based on content in the activity stream update. The method further may include adjusting a visibility level of the participant profile in the social networking interface based upon the calculated relevancy score. Adjusting the visibility level may include increasing the visibility level of the participant profile upon determining that the calculated relevancy score is greater than or equal to a first predefined threshold value. Adjusting the visibility level further may include decreasing the visibility level of the participant profile upon determining that the calculated relevancy score is less than a second predefined threshold value.

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: Embodiments relate to a system, program product, and method for use with an intelligent computer platform to decipher analogical phrases. An analogy list is obtained, each analogy within the analogy list having a known meaning, and receiving an analogy phrase. A verb is identified within the phrase and a verb definition list is generated. A subject is identified within the phrase and a subject definition list is generated. An adjective is identified within the phrase and an adjective definition list is generated, including filtering adjectives to accept adjective definitions associated with the identified subject. A set of outcomes is identified, incorporating the verb definition, subject definition, and adjective definition, and a corpus is searched for evidentiary use. The outcomes are ranked in accordance to evidentiary use found in the corpus the highest ranked outcome is outputted.

Abstract: Methods and systems privatize a dataset while controlling discoverability of patterns of the dataset. In an embodiment, values are assigned to discoverable patterns of a dataset. Privacy constraints are determined to privatize the dataset. Pattern constraints are determined to preserve a first set of patterns of the dataset and to conceal a second set of patterns of the dataset. A model is generated to satisfy all of the privacy constraints and a subset of the pattern constraints that do not conflict with the privacy constraints, with minimal loss of data. The dataset is modified based on the model. Discoverable patterns of the modified database are determined from the subset of privacy constraints. And a monetary value of the modified dataset is determined based on the patterns that remain discoverable in the modified dataset.

Abstract: A method, system and computer-usable medium for classifying a source document using sub-documents identified in the source document. The method, system, and computer-usable medium are used to access the source document from electronic memory. The source document is electronically searched to detect markers indicative of whether the source document includes one or more sub-documents. Incongruities in the source document are located using the detected markers and the source document is split into sub-documents at the located incongruities. Each of the sub-documents is classified. The sub-documents are joined as a re-assembled source document with classifications including classifications for one or more of the sub-documents.

Abstract: A method, computer system, and a computer program product for active machine learning is provided. The present invention may include annotating a plurality of data entries. The present invention may also include building a first dataset based on the annotated plurality of data entries. The present invention may then include receiving user feedback based on the built first dataset. The present invention may further include assigning a plurality of weights to a plurality of data entry subsets. The present invention may also include generating a second weighted dataset based on the received user feedback.

Abstract: An approach is described for adjusting prominence of a participant profile in a social networking interface. An associated method may include receiving an activity stream update of the participant and calculating a relevancy score based on content in the activity stream update. The method further may include adjusting a visibility level of the participant profile in the social networking interface based upon the calculated relevancy score. Adjusting the visibility level may include increasing the visibility level of the participant profile upon determining that the calculated relevancy score is greater than or equal to a first predefined threshold value. Adjusting the visibility level further may include decreasing the visibility level of the participant profile upon determining that the calculated relevancy score is less than a second predefined 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 computer-implemented method includes receiving first lossy converted documents. The computer-implemented method includes generating corrected documents for the first lossy converted documents. Each of the corrected documents includes edit markers that reflect structure changes relative to a corresponding document of the first lossy converted documents. The computer-implemented method includes generating feature vectors for the first lossy converted documents. The feature vectors include structure features of the first lossy converted documents. The computer-implemented method includes training one or more models based on the structure features and the edit markers. The computer-implemented method includes applying the trained one or more models to second lossy converted documents to determine proposed structure edits. The computer-implemented method includes transforming the second lossy converted documents to second corrected documents by applying one or more of the proposed structure edits.