Abstract: Embodiments for assisting pronunciation correction are described. A representation of a user pronunciation of an utterance is received. A representation of a target pronunciation of the utterance is identified. The representation of the user pronunciation of the utterance is compared to the representation of the target pronunciation of the utterance. A recommendation associated with correcting the user pronunciation of the utterance is generated based on the comparing of the representation of the user pronunciation of the utterance to the representation of the target pronunciation of the utterance and information associated with the user.

Abstract: Embodiments facilitating enhanced synergy between machine learning models and annotators in a computing environment by a processor. Annotation tasks may be coordinated between one or more annotators and machine learning models based on one or more annotator preferences and data annotation requirements of a machine learning model. The one or more annotator preferences and the data annotation requirements for coordinating the annotation tasks may be learned over a period of time.

Abstract: Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.

Abstract: In an approach to explaining probabilistic answers through contextualization, one or more computer processors receive a query associated with a probability value of a first event from a user. One or more computer processors parse the query into one or more constituent parts. Based on the one or more constituent parts, one or more computer processors determine the first event. One or more computer processors query a probability value of the first event, where the second event is similar to the first event. One or more computer processors determine the probability value of the first event and the probability value of the second event are known. One or more computer processors fetch the probability value of the first event and the probability value of the second event. One or more computer processors display the probability value of the first event and the probability value of the second event.

Abstract: Content can be dynamically associated to an annotator based on machine learning of annotator expertise and dynamically maintaining a set of labels and relationships among the labels. A probable group of labels associated with the content can be determined by a first machine learning model. Using a set of labels and relationships among the set of labels maintained dynamically, a second machine learning model can select an annotator having subject matter expertise associated with the probable group of labels. The first machine learning model and the second machine learning model can be retrained based on annotations performed on the content by the annotator as feedback. A third machine learning model can dynamically maintain the set of labels and the relationships among the set of labels.

Abstract: An information retrieval response may be augmented, based upon a query, with a plurality of selected causality data relating to the query. The information retrieval response may be generated from an information retrieval system.

Abstract: A method including: generating, from a text corpus, a lexicon of unigrams and bigrams comprising an embedding for each of said unigrams and bigrams; training a machine learning classifier on a training set comprising a subset of said lexicon, wherein each of said unigrams and bigrams in said subset has a sentiment label; applying said machine learning classifier to said lexicon, to (i) predict a sentiment of each of said unigrams and bigrams, and (ii) update said lexicon with the predicted sentiments; and performing statistical analysis on said updated lexicon, to extract one or more sentiment composition lexicons, wherein each of said one or more sentiment composition lexicons is associated with a sentiment composition class.

Abstract: Embodiments for assisting pronunciation correction are described. A representation of a user pronunciation of an utterance is received. A representation of a target pronunciation of the utterance is identified. The representation of the user pronunciation of the utterance is compared to the representation of the target pronunciation of the utterance. A recommendation associated with correcting the user pronunciation of the utterance is generated based on the comparing of the representation of the user pronunciation of the utterance to the representation of the target pronunciation of the utterance and information associated with the user.

Abstract: Various embodiments are provided for providing causality augmented information in a computing environment by a processor. An information retrieval response may be augmented, based upon a query, with a plurality of selected causality data relating to the query. The information retrieval response may be generated from an information retrieval system.

Abstract: Embodiments for generating text with a target style are provided. A target corpus is analyzed to determine a style representation associated with the target corpus. A source text is analyzed to determine a meaning representation associated with the source text. A target text is generated utilizing the target style representation associated with the target corpus and the meaning representation associated with the source text.

Abstract: Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.

Abstract: Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.

Abstract: A method including: generating, from a text corpus, a lexicon of unigrams and bigrams comprising an embedding for each of said unigrams and bigrams; training a machine learning classifier on a training set comprising a subset of said lexicon, wherein each of said unigrams and bigrams in said subset has a sentiment label; applying said machine learning classifier to said lexicon, to (i) predict a sentiment of each of said unigrams and bigrams, and (ii) update said lexicon with the predicted sentiments; and performing statistical analysis on said updated lexicon, to extract one or more sentiment composition lexicons, wherein each of said one or more sentiment composition lexicons is associated with a sentiment composition class.

Abstract: Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.