Abstract: Techniques that facilitate generating and executing an optimal dialogue strategy are provided. In one example, a system includes an information gain component and a question selector component. The information gain component estimates information gain data associated with first dialogue data of an information system. The information gain data is indicative of an amount of change in entropy associated with the first dialogue data. The question selector component selects between second dialogue data associated with a first question strategy and third dialogue data associated with a second question strategy based on the information gain data.

Abstract: Techniques that facilitate generating and executing an optimal dialogue strategy are provided. In one example, a system includes an information gain component and a question selector component. The information gain component estimates information gain data associated with first dialogue data of an information system. The information gain data is indicative of an amount of change in entropy associated with the first dialogue data. The question selector component selects between second dialogue data associated with a first question strategy and third dialogue data associated with a second question strategy based on the information gain data.

Abstract: A method of training a chatbot comprises obtaining a set of utterances. The method also comprises identifying a set of intents associated with utterances within the set of utterances. The method further comprises organizing intents within the set of intents hierarchically. This may result in a customized intent hierarchy. The method further comprises created a list of intents within the customized intent hierarchy.

Abstract: Embodiments for building domain models from dialog interactions by a processor. A domain knowledge may be elicited from one or more dialog interactions with one or more users according to one or more dialog strategies. One or more domain models may be built and/or enhanced according to the domain knowledge.

Abstract: Techniques are provided for reinforcement learning software agents enhanced by external data. A reinforcement learning model supporting the software agent may be trained based on information obtained from one or more knowledge stores, such as online forums. The trained reinforcement learning model may be tested in an environment with limited connectivity to an external environment to meet performance criteria. The reinforcement learning software agent may be deployed with the tested and trained reinforcement learning model within an environment to autonomously perform actions to process requests.

Abstract: Methods and arrangements for assessing impact of an event on a network. An event notification is received relative to traffic in the network. Metadata are extracted from the notification, and the extracted metadata are converted into a predetermined format for processing. The converted metadata are received, and an impact of the event on traffic in the network is determined. Other variants and embodiments are broadly contemplated herein.

Abstract: A conversational agent rating method, system, and computer program product include receiving a plurality of raw score rankings of a conversational agent from a third party, converting the plurality of raw score rankings into qualitative scores, and generating a rating for the conversational agent by combining the qualitative scores.

Abstract: Embodiments relate to a system, program product, and method for automatically determining which activation data points in a neural model have been poisoned to erroneously indicate association with a particular label or labels. A neural network is trained using potentially poisoned training data. Each of the training data points is classified using the network to retain the activations of the last hidden layer, and segment those activations by the label of corresponding training data. Clustering is applied to the retained activations of each segment, and a cluster assessment is conducted for each cluster associated with each label to distinguish clusters with potentially poisoned activations from clusters populated with legitimate activations. The assessment includes executing a set of analyses and integrating the results of the analyses into a determination as to whether a training data set is poisonous based on determining if resultant activation clusters are poisoned.

Abstract: Embodiments relate to a system, program product, and method for automatically determining which activation data points in a neural model have been poisoned to erroneously indicate association with a particular label or labels. A neural network is trained network using potentially poisoned training data. Each of the training data points is classified using the network to retain the activations of the last hidden layer, and segment those activations by the label of corresponding training data. Clustering is applied to the retained activations of each segment, and a cluster assessment is conducted for each cluster associated with each label to distinguish clusters with potentially poisoned activations from clusters populated with legitimate activations. The assessment includes analyzing, for each cluster, a distance of a median of the activations therein to medians of the activations in the labels.

Abstract: A computer receives a product or service name for competitive analysis. The computer determines a plurality of dimensions for competitive analysis of the product or service. The computer collects product or service data regarding a product or service associated with the product or service name and one or more competing products or services. The computer performs, using the plurality of dimensions, natural language processing on the collected product or service data. The computer calculates, using results of the natural language processing, a product or service competitiveness score. The computer outputs the product or service competitiveness score.

Abstract: Various embodiments are provided for applying judgment reasoning knowledge in a dialog system in a computing environment by a processor. A determination is made that a response to a query during a dialog using the dialog system fails to comply with one or more expected response patterns to one of a plurality of query responses. An updated response may be provided to the query using judgment reasoning knowledge for matching the updated response with the one or more expected response patterns.

Abstract: A computer-implemented dynamic road stretch dividing method, the method comprising: determining a current lane distribution of partitions of a road stretch; calculating a new lane distribution of the road stretch to ameliorate traffic based on a pragmatic factor; changing an alignment of the partitions of the current lane distribution to obtain the new lane distribution; and updating the pragmatic factor based on at least one of an external policy and a constraint input by a user.

Abstract: Methods and arrangements for displaying results of one or more query searches. Query search results are obtained and there are determined, from the query search results, a best object type, a best instance of the best object type and one or more alternative object types, wherein determining a best object type includes consulting a collection of domain ontologies. The search results are displayed on a single screen via showing the best object type, the best instance of the best object type and the one or more alternative object types. Other variants and embodiments are broadly contemplated herein.

Abstract: A bias detection method, system, and computer program product to evaluate bias in an artificial intelligence service include selecting a bias context, the bias context having a bias specification associated with the bias context, generating test data for determining the bias in the artificial intelligence service based on the bias specification and the bias context, and testing the artificial intelligence service for the bias with the generated test data.

Abstract: Embodiments of the present invention provide a system for implementing multi-turn dialogs. The system performs a method that includes receiving a series of user utterances, generating a series of responsive system utterances, and labeling the series of responsive system utterances to generate training data for training a dialog management policy. The labeling includes executing a reward function at each turn of a dialog, in which for each turn of the dialog the reward function is configured to output a reward value that is based at least in part on an accuracy of the responsive system utterance of the turn and on number of dialog turns elapsed.

Abstract: Techniques for autonomously generating a domain model and/or an action model based on unstructured data are provided. In one example, a computer implemented method can comprise extracting, by a system operatively coupled to a processor, a plurality of actions from a non-numerical language. The plurality of actions can achieve a goal. The computer-implemented method can also comprise generating, by the system, a domain model based on the plurality of actions. Further, the computer-implemented method can comprise generating, by the system, an action model based on the domain model. In various embodiments, the action model can comprise an action transition for accomplishing the goal.

Abstract: Techniques for autonomously generating a domain model and/or an action model based on unstructured data are provided. In one example, a computer implemented method can comprise extracting, by a system operatively coupled to a processor, a plurality of actions from a non-numerical language. The plurality of actions can achieve a goal. The computer-implemented method can also comprise generating, by the system, a domain model based on the plurality of actions. Further, the computer-implemented method can comprise generating, by the system, an action model based on the domain model. In various embodiments, the action model can comprise an action transition for accomplishing the goal.

Abstract: Techniques that facilitate generating and executing an optimal dialogue strategy are provided. In one example, a system includes an information gain component and a question selector component. The information gain component estimates information gain data associated with first dialogue data of an information system. The information gain data is indicative of an amount of change in entropy associated with the first dialogue data. The question selector component selects between second dialogue data associated with a first question strategy and third dialogue data associated with a second question strategy based on the information gain data.

Abstract: A bias detection method, system, and computer program product to evaluate bias in an artificial intelligence service include selecting a bias context, the bias context having a bias specification associated with the bias context, generating test data for determining the bias in the artificial intelligence service based on the bias specification and the bias context, and testing the artificial intelligence service for the bias with the generated test data.

Abstract: Embodiments for building domain models from dialog interactions by a processor. A domain knowledge may be elicited from one or more dialog interactions with one or more users according to one or more dialog strategies. One or more domain models may be built and/or enhanced according to the domain knowledge.