Abstract: A dialogue complexity assessment method, system, and computer program product including calculating a complexity utilizing domain-dependent terms and domain-independent terms of a dialogue, where the dialogue includes dialogue data from contact centers of service providers.

Abstract: The disclosure deals with a system and method for improved representation and retrieval of recipes or workflows. Recipes or workflows such as for preparing food or assembling furniture or performing other complex activities exist as textual or image documents, which makes it difficult for machines to read, reason, and handle ambiguity. The present disclosure provides a Rich Recipe Representation (“R3”), which is enhanced with additional knowledge such as outcomes like allergen information, possible failures, and solutions for each atomic step (such as a cooking step). The disclosed R3 is used in a web-based decision support system that helps users perform constrained queries using multiple modalities while also monitoring execution of an agent cooking or otherwise acting based on it.

Abstract: A method and system relates to assigning ratings (i.e., labels) to convey the trustability of AI systems grounded in its cause-and-effect behavior of significant inputs and outputs of the AI. Sentiment Analysis Systems (SASs) are data-driven Artificial Intelligence (AI) systems that, given a piece of text, assign a score conveying the sentiment and emotion intensity. The present disclosure uses the approach that protected attributes like gender and race influence the output (sentiment) given by SASs or if the sentiment is based on other components of the textual input, e.g., chosen emotion words. The presently disclosed rating methodology assigns ratings at fine-grained and overall levels, to rate SASs grounded in a causal setup, and provides an open-source implementation of both SASs—two deep-learning based, one lexicon-based, and two custom-built models—for this rating implementation. This allows users to understand the behavior of SAS in real-world applications.

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: 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: Event intensity assessment can include detecting an event description within textual input received via a data communication network. An event-correlated data structure based on the event can be generated, the event-correlated data structure including an event descriptor corresponding to the event. An event sentiment can be determined based on the event descriptor and an event impact based on a quantitative temporal-spatial measure corresponding to the event. An event intensity can be determined based on the event sentiment and event impact. A GUI can be modified in response to the event intensity exceeding a predetermined threshold. The GUI can be modified to indicate the event and the event intensity.

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: The disclosure deals with a system and method for building teams in response to a teaming opportunity. In one exemplary embodiment disclosed herewith, a system and method for building teams for Request for Proposals (RFPs) is described where potential team participants are researchers at one or more institutions. A computer-based method and computer system, given RFPs from funding agencies like NSF, DOE and NASA, recommends a team of experts from various faculties and departments of the organization, like a university, that would best fit the needs of the RFP and have a high chance of putting a successful proposal together. The system generates teams that may match the requirements of an RFP. In addition, the system optimizes the list of teams to maximize winning success and to reduce redundancy. The system input includes RFPs and the researchers' public information. The system output is a list of proposed teams, each team with two or more members.

Abstract: Techniques facilitating estimating and visualizing entity to agent collaboration to facilitate automated plan generation are provided. In one example, a computer-implemented method comprises generating, by a device operatively coupled to a processor, a plan based on receiving first input data associated with an instance model. The computer-implemented method also comprises generating, by the device, a revised plan based on receiving second input data, associated with a revised instance model, from an entity. Furthermore, the computer-implemented method comprises, tracking, by the device, a contribution of the entity as a function of a modification from the instance model to the revised instance model.

Abstract: A dialogue complexity assessment method, system, and computer program product including calculating a complexity utilizing domain-dependent terms and domain-independent terms of a dialogue, where the dialogue includes dialogue data from contact centers of service providers.

Abstract: The disclosure deals with a system and method for improved general task-oriented virtual assistants (VAs). The presently disclosed framework incorporates discovery of knowledge from online sources to accomplish tasks (open world), user-specific knowledge for personalization, and domain-specific knowledge for context adaptation to recommend and assist the users over procedural tasks such as cooking and Do-it-Yourself (DIY) tasks. The approach also focuses on content curation for fault-tolerant execution to ensure the end goal is reached despite common failures.

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 dialogue complexity assessment method, system, and computer program product including calculating a complexity utilizing domain-dependent terms and domain-independent terms of a dialogue, where the dialogue includes dialogue data from contact centers of service providers.

Abstract: Various embodiments are provided for using a dialog system for integrating multiple domain learning and problem solving for a user in a computing environment by a processor. One or more problem instances may be defined for one or more selected domains in a multi-domain database according to a problem instance template, identified user intent, links to one or more problem solvers associated with the one or more selected domains, or a combination thereof. A dialog plan may be determined for the one or more problem instances using a dialog system associated with the multi-domain database, wherein each record in the multi-domain database corresponds to a selected database for the one or more selected domains. A solution may be provided to the user for the one or more problem instances. One or more preferences of a user may be learned according to the solution.

Abstract: Various embodiments are provided for integrating multiple domain learning and personalization in a dialog system for a user in a computing environment by a processor. One or more problem instances may be defined for multiple domains according to a problem instance template, identified user intent, links to one or more problem solvers associated with the multiple domains, or a combination thereof. A dialog plan may be determined to further define the one or more problem instances in response to user input. A solution may be provided to the user for the one or more problem instances.

Abstract: A method, computer system, and a computer program product for chatbot generating is provided. The present invention may include determining one or more entities based on at least one column header of a dataset. The present invention may include determining one or more actions based on an associated row, the associated row corresponding to the at least one column header. The present invention may include generating a conversation environment, wherein the conversation environment comprises pairing the one or more entities with the one or more supplied intents of a chatbot workspace and pairing the one or more actions with one or more supplied utterances of the chatbot workspace.

Abstract: A method, computer system, and a computer program product for competitive analysis is provided. The present invention may include identifying one or more potential competitors by searching a knowledge corpus using one or more see terms. The present invention may include determining one or more competitors by eliminating at least one potential competitor. The present invention may include generating a competitive analyst report.

Abstract: A method and device for synthesizing adaptive defenses of artificial intelligence (AI) systems against adversarial attacks. The method comprises, during a design phase, creating a library of weak defenses (WDs); preprocessing the WDs in the library; selecting a subset W of WDs from the WDs in the library; and, during a deployment phase, synthesizing an ensemble strategy based on an input of the selected subset W of WDs, the ensemble strategy used as a defense against adversarial attacks.

Abstract: Techniques are provided for assigning a bias rating to a service based on bias and/or anti-bias testing. For example, unbiased data can be input to the service to, e.g., determine whether the service introduces elements of bias. As another example, biased data can be input to the service to determine whether the service provides elements of anti-bias. In one example, a computer-implemented method comprises selecting, by a device operatively coupled to a processor, source data configured according to a bias specification indicating a criterion that defines bias. The computer-implemented method can comprise determining whether bias exists in output data of the service and determining a bias rating based on the determining whether bias exists in the output data. The computer-implemented method can further comprise assigning the bias rating to the service.

Abstract: Embodiments for learning personalized actionable domain models by a processor. A domain model may be generated according to a plurality of actions, extracted from one or more online data sources, of a plurality of cluster representatives. The plurality of actions achieve a goal. A hierarchical action model may be generated based on probabilities of the domain model and the plurality of actions. The hierarchical action model comprises a sequence of actions of the plurality of actions for achieving the goal. The hierarchical action model may be personalized by filtering to a selected set of actions according to weighted actions of the plurality of actions.