Abstract: A pre-trained natural language processing machine learning model is received. The pre-trained natural language processing machine learning model is tuned. A workflow to be implemented by a chatbot to complete a task-oriented dialog is received. A representation of one or more plan steps based on a current progression state of the workflow is dynamically determined. At least the representation of the one or more plan steps is provided as an input to the pre-trained natural language processing machine learning model to guide the pre-trained natural language processing machine learning model. An output action and/or an utterance for the task-oriented dialog is received from the pre-trained natural language processing machine learning model.

Abstract: Systems and methods are disclosed that provide smart alerts to users, e.g., alerts to users about diabetic states that are only provided when it makes sense to do so, e.g., when the system can predict or estimate that the user is not already cognitively aware of their current condition, e.g., particularly where the current condition is a diabetic state warranting attention. In this way, the alert or alarm is personalized and made particularly effective for that user. Such systems and methods still alert the user when action is necessary, e.g., a bolus or temporary basal rate change, or provide a response to a missed bolus or a need for correction, but do not alert when action is unnecessary, e.g., if the user is already estimated or predicted to be cognitively aware of the diabetic state warranting attention, or if corrective action was already taken.

Abstract: An indication to predict one or more additional steps to be added to a partially specified computerized workflow based at least in part on the partially specified computerized workflow is received. Text descriptive of at least a portion of the partially specified computerized workflow is generated. Machine learning inputs based at least in part on the descriptive text are provided to a machine learning model to determine an output text descriptive of the one or more additional steps to be added. One or more processors are used to automatically implement the one or more additional steps to be added to the partially specified computerized workflow.

Abstract: A user provided text description of at least a portion of a desired workflow is received. Context information associated with the desired workflow is determined. Machine learning inputs based at least in part on the text description and the context information are provided to a machine learning model to determine an implementation prediction for the desired workflow. One or more processors are used to automatically implement the implementation prediction as a computerized workflow implementation of at least a portion of the desired workflow.

Abstract: Content of a dialog between at least two communication parties to resolve a task is received. A specification associated with at least a portion of eligible steps of a workflow is received. Machine learning input data is determined based on the received content of the dialog and the received specification. The determined machine learning input data is processed using a trained machine learning model executing on one or more hardware processors to automatically predict a sequence of workflow steps representing the dialog.

Abstract: Systems and methods relating to neural networks. More specifically, the present invention relates to complex valued gating mechanisms which may be used as neurons in a neural network. A novel complex gated recurrent unit and a novel complex recurrent unit use real values for amplitude normalization to stabilize training while retaining phase information.