Abstract: The present teaching relates to method system, and medium for generating knowledge for a chat bot. Training data are used to learn and generating knowledge and are received with at least some labeled training seeds and unlabeled conversation data. The training data are parsed and various linguistic elements are extracted therefrom. Such linguistic elements are then used to perform automated learning in accordance with at least one label used in labeling the training seeds. Based on the automated learning, at least one model associated with the at least one label is generated from the training data.

Abstract: The present teaching relates to developing a virtual agent. In one example, a plurality of graphical objects is presented to a user via a bot design programming interface. Each of the plurality of graphical objects represents a module corresponding to an action to be performed by the virtual agent. One or more inputs from the user are received, via the bot design programming interface, for selecting a set of graphical objects from the plurality of graphical objects. The one or more inputs provide information of a first order of the set of graphical objects. A plurality of modules represented by the set of graphical objects is identified. Based on the one or more inputs, a second order of the plurality of modules is determined based on the first order. The plurality of modules is integrated in the second order to generate a customized virtual agent for executing an associated task according to the second order.