Abstract: There is provided a dialogue system comprising: an input for obtaining an input signal relating to speech or text input provided by a user; an output for outputting speech or text information specified by a determined dialogue act; and a processor configured to: determine dialogue information from the input signal; determine the dialogue act based on the determined dialogue information, wherein determining the dialogue act comprises: selecting a next state from a plurality of states, wherein each of the plurality of states comprises information specifying a dialogue act and transition information specifying a transition to another state, the transitions defining one or more dialogue pathways, wherein selecting the next state comprises selecting a state which is specified by the transition information in a current state or selecting a state which is specified by a rule in a first set of one or more rules.

Abstract: A method of obtaining a response to a query inputted by a user, the method comprising: receiving a user inputted query; encoding said query to produce a context vector; retrieving responses with associated response vectors; scoring response vectors in the database against the context vector wherein the scoring is a measure of the similarity between the context vector and a response vector; and outputting the responses with the closest response vectors, wherein encoding said query to produce a context vector comprises using a pre-trained model, wherein said pre-trained model has been trained using corresponding queries and responses such that an encoding is used that maximises the similarity between the response vector and context vector for a corresponding query and response.