Abstract: An approach is provided to receive audible speech and convert the received speech to text while the audible speech is being delivered to a user. An annotation candidate is identified in the text and an annotation reference relating to the identified annotation candidate is retrieved and presented to the user.

Abstract: A method for selective computation using analytic functions is provided in the illustrative embodiments. An object graph and information about a change therein is received. The object graph includes several objects representing several resources in an environment as well as a set of analytic function instances in relation to the objects. A set of analytic function dependencies is determined. A first analytic function instance in the set of analytic function instances that has to be re-executed based on the change is identified. A re-computation graph is computed using the analytic function instance and presented. The change may be an addition, a deletion, a modification, or a combination thereof. The change may be a change in an object, in a relationship between two objects, in a relationship between an object in and an analytic function instance in the set of analytic function instances, or in an analytic function instance.

Abstract: A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for providing confidence rankings based on temporal semantics. Responsive to receiving an input question, a set of candidate answers is identified from a knowledge domain based on a correlation between an identified one or more predicates and an identified one or more arguments to the knowledge domain. A confidence score is associated with each of the candidate answers and each confidence score associated with each candidate answer is refined based on a set of temporal characteristics identified in the input question. A set of temporally refined candidate answers is then provided to the user.

Abstract: A system, and computer usable program product for selective computation using analytic functions are provided in the illustrative embodiments. An object graph and information about a change therein is received. The object graph includes several objects representing several resources in an environment as well as a set of analytic function instances in relation to the objects. A set of analytic function dependencies is determined. A first analytic function instance in the set of analytic function instances that has to be re-executed based on the change is identified. A re-computation graph is computed using the analytic function instance and presented. The change may be an addition, a deletion, a modification, or a combination thereof. The change may be a change in an object, in a relationship between two objects, in a relationship between an object in and an analytic function instance in the set of analytic function instances, or in an analytic function instance.

Abstract: Mechanisms are provided for generating a lexical resource for linguistic analysis. A document data structure is received that comprises a renaming directive and filter logic is applied to the document data structure to identify the renaming directive within the document data structure. The renaming directive is analyzed to identify a relationship between semantic concepts represented by the renaming directive that are to be used to update a lexical resource based on the renaming directive. The lexical resource is updated based on results of analyzing the renaming directive. The updated lexical resource is output to a linguistic analysis system which performs linguistic analysis of a portion of textual content based on the updated lexical resource.

Abstract: Mechanisms for ingesting a document from a corpus of documents for use by a Question and Answer (QA) system are provided. The mechanisms receive a document from a corpus of documents and generate one or more titles for the document based on an analysis of content of the document. The mechanisms generate score values for the titles based on a measure of a degree to which the titles represent the content of the document. The mechanisms store the score values in association with the titles as document metadata associated with the document and output the document and document metadata to the QA system. The QA system utilizes the document metadata and document to generate a candidate answer to an input question.

Abstract: A mechanism is provided, in a question answering (QA) system, for performing persona-based question answering is provided. An identification of a requested persona is received from a user along with a natural language question input specifying an input question to be answered by the QA system. Responsive to receiving the requested persona, components of the QA system are customized to answer questions from a viewpoint of the requested persona. An answer to the input question is generated from the viewpoint of the requested persona based on the customization of the components of the QA system. The answer to the input question is output in a form representative of the requested persona.

Abstract: Travel itineraries are automatically prepared based upon user interests and sentiments inferred by deep semantic analysis of user-commented and user-preferred digital works of literature by receiving interests and associated sentiment levels for at least one user according to a deep semantic analysis of a plurality of works of literature, wherein the works of literature have been rated, commented, or both rated and commented by the user; searching repositories of travel items to find one or more matching travel items to the received more interests and associated sentiment levels; and preparing at least one travel itinerary including at least one found matching travel item. Travel itineraries may be prepared responsive to a user-initiated trip planning session, responsive to notification of a new travel item's availability, periodically, or a combination thereof.

Abstract: A digital work of literature is vocalized using enhanced text-to-speech (TTS) controls by analyzing a digital work of literature using natural language processing to identify speaking character voice characteristics associated with context of each quote as extracted from the first work of literature; converting the character voice characteristics to audio metadata to control text-to-speech audio synthesis for each quote; transforming the audio metadata into text-to-speech engine commands, each quote being associated with audio synthesis control parameters for the TTS in the context of each the quotes in the work of literature; and inputting the commands to a text-to-speech engine to cause vocalization of the work of literature according to the words of each quote, character voice characteristics of corresponding to each quote, and context corresponding to each quote.

Abstract: A system, and computer program product for disambiguation of dependent referring expression in natural language processing are provided in the illustrative embodiments. A portion of a document in a set of document is selected, the portion including a set of dependent referring expression instances. The portion is filtered to identify an instance from a set of dependent referring expression instances by using a linguistic characteristic of the instance, the instance of dependent referring expression referring to a full expression occurring in the set of documents. The full expression is located in one member document in the set of documents by locating where the dependent referring expression is defined to be a stand-in for the full expression. The instance is resolved using the full expression such that information about the full expression is available at a location of the instance.

Abstract: A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for utilizing temporal indicators to weight semantic values. A set of temporal characteristics is identified of a set of initial candidate answers. For each initial candidate answer in the set of initial candidate answers: a distance value is generated for each of the set of temporal characteristics of the set of initial candidate answers, a multiplier value is determined with which to weight an initial confidence score associated with the initial candidate answer using the distance value; a sentiment value is determined of the initial candidate answer, and a final weight value is determined using the multiplier value, the sentiment value, and the initial confidence score associated with the initial candidate answer. A set of temporally refined candidate answers is then provided using the determined final weight values.

Abstract: A computer implemented method of generating a language section from tabular data in an electronic document may include identifying, in a first tabular portion of the electronic document, a set of categories used to organize tabular data. The method may include identifying a content characteristic for each category of the set of categories in the first tabular portion. And the method may include generating a first language section from at least two distinct categories of the set of categories, wherein a format of the first language section is based on the content characteristics for the at least two distinct categories.

Abstract: A computer implemented method of generating a language section from tabular data in an electronic document may include identifying, in a first tabular portion of the electronic document, a set of categories used to organize tabular data. The method may include identifying a content characteristic for each category of the set of categories in the first tabular portion. And the method may include generating a first language section from at least two distinct categories of the set of categories, wherein a format of the first language section is based on the content characteristics for the at least two distinct categories.

Abstract: A mechanism is provided in a data processing system for rating difficulty of a question. The mechanism receives an input question and generates one or more candidate answers from a corpus of knowledge using a pipeline of software engines. The pipeline of software engines generates a plurality of features extracted from the question, the one or more candidate answers, or the corpus of knowledge. The mechanism then generates a question difficulty score based on the plurality of features using a machine learning model. The machine learning model maps features to assigned weights for scaling the difficulty score.

Abstract: An approach is provided in which a voice management system generates multiple audio test recordings using multiple text-to-speech (TTS) voices that have different acoustic properties. The voice management system determines that a comparison between a first one of the TTS voices and a second one of the TTS voices reaches an acoustic differentiation threshold and, as a result, assigns the first TTS voice to a first character and assigns the second TTS voice to a second character. In turn, the voice management system generates a narrative audio work utilizing the first TTS voice corresponding to the first character and the second TTS voice corresponding to the second character.

Abstract: A method for minimizing undesirable user responses in automated business processes design is provided in the illustrative embodiments. A user response is identified in an interaction between a user and an automated business process. Using sentiment analysis, a determination is made that the user response comprises an undesirable response based on an undesirable emotional state of the user. A modification is selected, wherein the modification causes a change in the interaction to minimize the undesirable response. The modification is applied to the automated business process to cause the change in a future portion of the interaction.

Abstract: A system, and computer program product for minimizing undesirable user responses in automated business processes design are provided in the illustrative embodiments. A user response is identified in an interaction between a user and an automated business process. Using sentiment analysis, a determination is made that the user response comprises an undesirable response based on an undesirable emotional state of the user. A modification is selected, wherein the modification causes a change in the interaction to minimize the undesirable response. The modification is applied to the automated business process to cause the change in a future portion of the interaction.

Abstract: A digital work of literature is vocalized using enhanced text-to-speech (TTS) controls by analyzing a digital work of literature using natural language processing to identify speaking character voice characteristics associated with context of each quote as extracted from the first work of literature; converting the character voice characteristics to audio metadata to control text-to-speech audio synthesis for each quote; transforming the audio metadata into text-to-speech engine commands, each quote being associated with audio synthesis control parameters for the TTS in the context of each the quotes in the work of literature; and inputting the commands to a text-to-speech engine to cause vocalization of the work of literature according to the words of each quote, character voice characteristics of corresponding to each quote, and context corresponding to each quote.

Abstract: Mechanisms are provided for performing tabular data correction in a document. Tabular data is received and analyzed to identify at least one portion of the tabular data having an erroneous/missing data value. A functional dependency of the at least one portion of the tabular data on one or more other portions of the tabular data is determined. A correct data value for the erroneous or missing data value of the at least one portion of the tabular data is determined based on the functional dependency of the at least one portion. In addition, the tabular data is modified to replace the erroneous or missing data value with the correct data value and thereby generate a modified table data. A processing operation is then performed on the modified table data to generate a resulting output.

Abstract: A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for utilizing temporal indicators to weight semantic values. A set of temporal characteristics is identified of a set of initial candidate answers. For each initial candidate answer in the set of initial candidate answers: a distance value is generated for each of the set of temporal characteristics of the set of initial candidate answers, a multiplier value is determined with which to weight an initial confidence score associated with the initial candidate answer using the distance value; a sentiment value is determined of the initial candidate answer, and a final weight value is determined using the multiplier value, the sentiment value, and the initial confidence score associated with the initial candidate answer. A set of temporally refined candidate answers is then provided using the determined final weight values.