Abstract: Mechanisms for classifying electronic documents as to representation of natural conversations are provided. The mechanisms train one or more computer models to identify instances of natural conversation features in a plurality of natural conversation features. The trained computer model(s) process a document to identify instances of natural conversation features within the document. The mechanisms generate quantitative measures of conversational representation based on the identified instances of natural conversation features. The mechanisms classify the document based on the quantitative measures of conversational representation into one of a plurality of predefined classes of conversational representation, and outputting the classification for performance of a downstream computing operation based on the classification of the document.

Abstract: According to one embodiment, a method, computer system, and computer program product for generating natural conversation content for training conversational artificial intelligence (AI) systems is provided. The present invention may include receiving conversation content comprising one or more conversation sequences; assigning one or more labels to one or more utterances comprising the conversation sequences using a machine learning-based intent classifier to produce a plurality of labeled conversation content; determining if a confidence score for at least one of the assigned labels is below a predetermined threshold; determining at least one variant operation of a plurality of variant operations to perform on the labeled conversation content using a natural conversation variator; and performing the at least one operation of the plurality of variant operations on the labeled conversation content using the natural conversation variator to generate one or more variations of the labeled conversation content.

Abstract: A method for automatically providing real-time navigation directions using one or more vehicle components is provided. The method may further include, in response to receiving and identifying navigation direction data from a navigation service provider, converting the navigation direction data into different electrical communications to different vehicle components that may include one or more combinations of a light indicator component, a sound indicator component, and a vibration indicator component associated with a vehicle. The method may also include automatically presenting the real-time navigation directions using the different vehicle components by automatically transmitting the electrical communications based on the navigation direction data to the one or more combinations of the light indicator component, the sound indicator component, and the vibration indicator component.

Abstract: Techniques for personalizing an AI automated conversational system are provided. In one aspect, a method for personalizing an automated conversational system includes: making predictions of a familiarity of a user with concepts needed to understand a standard output utterance based on the familiarity of an aggregate of users and a background knowledge model of the concepts and related concepts, wherein the standard output utterance assumes that the concepts are known; and giving, by the automated conversational system, an output utterance that is tailored to the user given the predictions. For instance, the automated conversational system can give the standard output utterance to the user when it is predicted that the user is familiar with the concepts, or a nonstandard output utterance when it is it is predicted that the user is unfamiliar with at least one of the concepts.

Abstract: A computer-implemented method for generating an ontology-driven conversational interface includes generating an ontology from a description of a domain schema of a Data Analysis (DA) model, in which the DA model is a defined in terms of quantifiable, qualifying or categorical entities and their relationships as described by the domain schema. Conversational artifacts of a conversation space including a conversational pattern framework are generated by extracting DA-related intents, entities, and a dialog from the generated ontology for the conversational interface. A dialog logic table maps DA-related patterns to intents, extracted quantifiable, qualifying or categorical attributes to entities, and the dialog to user-prompts for one or more parameters in an identified DA pattern. The conversation space is integrated with at least one of an external data source or an analytics platform that stores and processes data.

Abstract: A computer-implemented method of voice-to-text tagging for transcription of a human voice signal by one of an automatic speech recognition system, or a natural conversation, includes generating a speech-to-text verbal transcript of the verbal vocalizations of an audio signal at a verbal timestamp of the audio signal. A voice-to-text non-verbal transcript of the one or more non-verbal vocalizations of the audio signal is generated at a non-verbal timestamp of the audio signal. The non-verbal transcript and the verbal transcript are combined to generate an enhanced transcript.

Abstract: Techniques for personalizing an AI automated conversational system are provided. In one aspect, a method for personalizing an automated conversational system includes: making predictions of a familiarity of a user with concepts needed to understand a standard output utterance based on the familiarity of an aggregate of users and a background knowledge model of the concepts and related concepts, wherein the standard output utterance assumes that the concepts are known; and giving, by the automated conversational system, an output utterance that is tailored to the user given the predictions. For instance, the automated conversational system can give the standard output utterance to the user when it is predicted that the user is familiar with the concepts, or a nonstandard output utterance when it is it is predicted that the user is unfamiliar with at least one of the concepts.

Abstract: A tool for providing dynamic context-based presentation adjustments across one or more computer devices. The tool receives a presentation from at least one of a plurality of user devices. The tool collects real-time contextual data associated with the presentation from at least one of the plurality of user devices. The tool analyzes the real-time contextual data utilizing a training model. The tool determines one or more adjustment actions based, at least in part, on the analysis of the real-time contextual data. The tool modifies the presentation in real-time using the one or more adjustment actions.

Abstract: A method, computer system, and a computer program product for contextual transformation is provided. The present invention may include providing a source application for transformation. The present invention may include transforming at least one selection within the source application. The present invention may include communicating the at least one transformed selection to a target application.

Abstract: In one general aspect, a computer-implemented method includes identifying current choices with different verbosity levels for a current turn in a conversation; normalizing multi-dimensional verbosity vectors for each of the current choices to obtain a normalized value for each of the current choices; determining a state definition for the current turn in the conversation, utilizing the normalized values for each of the current choices; providing the state definition for the current turn in the conversation and the normalized values for each of the current choices to a trained reinforcement learning module; receiving, from the trained reinforcement learning module, a score associated with each of the current choices for the current turn in the conversation; and selecting one of the current choices to be entered for the current turn in the conversation, based on the score associated with each of the current choices for the current turn in the conversation.

Abstract: A computer-implemented method for generating an ontology-driven conversational interface includes generating an ontology from a description of a domain schema of a Data Analysis (DA) model, in which the DA model is a defined in terms of quantifiable, qualifying or categorical entities and their relationships as described by the domain schema. Conversational artifacts of a conversation space including a conversational pattern framework are generated by extracting DA-related intents, entities, and a dialog from the generated ontology for the conversational interface. A dialog logic table maps DA-related patterns to intents, extracted quantifiable, qualifying or categorical attributes to entities, and the dialog to user-prompts for one or more parameters in an identified DA pattern. The conversation space is integrated with at least one of an external data source or an analytics platform that stores and processes data.

Abstract: A computer-implemented method of voice-to-text tagging for transcription of a human voice signal by one of an automatic speech recognition system, or a natural conversation, includes generating a speech-to-text verbal transcript of the verbal vocalizations of an audio signal at a verbal timestamp of the audio signal. A voice-to-text non-verbal transcript of the one or more non-verbal vocalizations of the audio signal is generated at a non-verbal timestamp of the audio signal. The non-verbal transcript and the verbal transcript are combined to generate an enhanced transcript.

Abstract: A method and system of automatically identifying topics of a conversation are provided. An electronic data package comprising a sequence of utterances between conversation entities is received by a computing device. Each utterance is classified to a corresponding social action. One or more utterances in the sequence are grouped into a segment based on a deep learning model. A similarity of topics between adjacent segments is determined. Upon determining that the similarity is above a predetermined threshold, the adjacent segments are grouped together. A transcript of the conversation including the grouping of the adjacent segments is stored in a memory.

Abstract: In one general aspect, a computer-implemented method includes identifying current choices with different verbosity levels for a current turn in a conversation; normalizing multi-dimensional verbosity vectors for each of the current choices to obtain a normalized value for each of the current choices; determining a state definition for the current turn in the conversation, utilizing the normalized values for each of the current choices; providing the state definition for the current turn in the conversation and the normalized values for each of the current choices to a trained reinforcement learning module; receiving, from the trained reinforcement learning module, a score associated with each of the current choices for the current turn in the conversation; and selecting one of the current choices to be entered for the current turn in the conversation, based on the score associated with each of the current choices for the current turn in the conversation.

Abstract: A method and system of automatically identifying topics of a conversation are provided. An electronic data package comprising a sequence of utterances between conversation entities is received by a computing device. Each utterance is classified to a corresponding social action. One or more utterances in the sequence are grouped into a segment based on a deep learning model. A similarity of topics between adjacent segments is determined. Upon determining that the similarity is above a predetermined threshold, the adjacent segments are grouped together. A transcript of the conversation including the grouping of the adjacent segments is stored in a memory.

Abstract: The present invention relates to methods of modulating traits, particularly production traits, in avians such as chickens. In particular, the invention relates to the in ovo delivery of a dsRNA molecule, especially siRNAs, to modify production traits in commercially important birds.

Abstract: The present invention relates to a polypeptide based toxin that originates from Clostridium perfringens. The invention further relates to immunogenic compositions comprising the toxin and methods to vaccinate animals, for example chickens, such that they are less susceptible to clostridial diseases. Methods to determine whether an animal has been exposed to the toxin, polynucleotides encoding the toxin and attenuated bacteria that express a reduced or less active form of the toxin are also disclosed.

Abstract: The present invention relates to nucleic acids and methods for modulating the sex of avians. In particular, the invention relates to the in ovo delivery of a dsRNA molecule, especially siRNAs, to increase the production of female birds.

Abstract: The present invention relates generally to the field of sex determination of animals. Provided are methods and agents to manipulate sex determination, particularly in avian animals such as chickens, through a male chromosome-linked testis (sex) regulatory gene. Expression or activity of the DMRT1 gene or protein is modulated to produce animals with displaying a phenotype sex that differs from their genotype.

Abstract: The present invention relates to methods for the delivery of biologically active polypeptides to a subject by colonizing non-pathogenic Gram negative bacteria. Also provided by this invention are methods of treating or preventing diseases by administering colonizing Gram negative bacteria that express one or more biologically active polypeptides. The colonizing non-pathogenic Gram negative bacteria may be administered in pharmaceutical formulations.