Abstract: A current observation expressed in natural language is received. Entities in the current observation are extracted. A relevant historical observation is retrieved, which has at least one of the entities in common with the current observation. The current observation and the relevant historical observation are combined as observations. The observations and a template list specifying a list of verb phrases to be filled-in with at least some of the entities are input to a neural network, which can output the template list of the verb phrases filled-in with said at least some of the entities. The neural network can include attention mechanism. A reward associated with the neural network's output can be received and fed back to the neural network for retraining the neural network.

Abstract: A computer-implemented method of integrating an Artificial Intelligence (AI) planner and a reinforcement learning (RL) agent through AI planning annotation in RL (PaRL) includes identifying an RL problem. A description received of a Markov decision process (MDP) having a plurality of states in an RL environment is used to generate an RL task to solve the RL problem. An AI planning model described in a planning language is received, and mapping state spaces from the MDP states in the RL environment to AI planning states of the AI planning model is performed. The RL task is generated with an AI planning task from the mapping to generate a PaRL task.

Abstract: Techniques regarding explanations for artificial intelligence recommendations are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory.

Abstract: An approach to determine the quality of encodings assigned to a word by a word embedding model. The approach may include determining the asymmetry of two embeddings associated with two words from a word embedding model. The asymmetry of the two words from a preexisting evocation dataset may be determined. The asymmetry of the two embeddings may be compared to the asymmetry from the evocation dataset to generate an encoding quality score.

Abstract: A current observation expressed in natural language is received. Entities in the current observation are extracted. A relevant historical observation is retrieved, which has at least one of the entities in common with the current observation. The current observation and the relevant historical observation are combined as observations. The observations and a template list specifying a list of verb phrases to be filled-in with at least some of the entities are input to a neural network, which can output the template list of the verb phrases filled-in with said at least some of the entities. The neural network can include attention mechanism. A reward associated with the neural network's output can be received and fed back to the neural network for retraining the neural network.

Abstract: An artificial intelligence (AI) platform to support random action replay for natural language (NL) learning. A NL conversation is explored to train a neural network. One or more tuples are leverage for the training, with each tuple representing an input action, a vector, an output action, and a reward value. An action is sampled from the vector, with the sampling including assessment of a corresponding first gradient. The first gradient is applied to selectively adjust the neural network. As NL input is received and applied to the selectively adjusted neural network, an output corresponding to the NL input is identified and a corresponding action is executed.

Abstract: Techniques regarding explanations for artificial intelligence recommendations are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory.

Abstract: Interoperability is enabled between participants in a network by determining values associated with a value metric defined for at least a portion of the network. Information flow is directed between two or more of the participants based at least in part on semantic models corresponding to the participants and on the values associated with the value metric. The semantic models may define interactions between the participants and define at least a portion of information produced or consumed by the participants. The determination of the values and the direction of the information flow may be performed multiple times in order to modify the one or more value metrics. The direction of information flow may allow participants to be deleted from the network, may allow participants to be added to the network, or may allow behavior of the participants to be modified.

Abstract: Interoperability is enabled between participants in a network by determining values associated with a value metric defined for at least a portion of the network. Information flow is directed between two or more of the participants based at least in part on semantic models corresponding to the participants and on the values associated with the value metric. The semantic models may define interactions between the participants and define at least a portion of information produced or consumed by the participants. The determination of the values and the direction of the information flow may be performed multiple times in order to modify the one or more value metrics. The direction of information flow may allow participants to be deleted from the network, may allow participants to be added to the network, or may allow behavior of the participants to be modified.