Learning End-to-End Goal-Oriented Dialog

End-to-end dialog systems, in which all components are learnt simultaneously, have recently obtained encouraging successes. However these were mostly on conversations related to chit-chat with no clear objective and for which evaluation is difficult. This paper proposes a set of tasks to test the capabilities of such systems on goal-oriented dialogs, where goal completion ensures a well-defined measure of performance. Built in the context of restaurant reservation, our tasks require to manipulate sentences and symbols, in order to properly conduct conversations, issue API calls and use the outputs of such calls. We show that an end-to-end dialog system based on Memory Networks can reach promising, yet imperfect, performance and learn to perform non-trivial operations. We confirm those results by comparing our system to a hand-crafted slot-filling baseline on data from the second Dialog State Tracking Challenge (Henderson et al., 2014a).