Demonstration of interactive dialog teaching for learning a practical end-to-end dialog manager

This is a demonstration of a platform for building practical, task-oriented, end-to-end dialog systems. Whereas traditional dialog systems consists of a pipeline of components such as intent detection, state tracking, and action selection, an endto-end dialog system is driven by a machine learning model which takes observable dialog history as input, and directly outputs a distribution over dialog actions. The benefit of this approach is that intermediate quantities such as intent or dialog state do not need to be labeled – rather, learning can be done directly on example dialogs. In practice, purely end-to-end methods can require large amounts of data to learn seemingly simple behaviors, such as sorting database results. This is problematic because when building a new dialog system, typically no in-domain dialog data exists, so data efficiency is crucial. Moreover, machine-learned models alone cannot guarantee practical constraints are followed – for example a bank would require that a user must be logged in before they are allowed to transfer funds. For these reasons, in past work we introduced Hybrid Code Networks (HCN) (Williams et al., 2017). HCNs make end-to-end learning practical by combining a recurrent neural network (RNN) with domain-specific software provided by the developer; domain-specific action templates; and a conventional entity extraction module for identifying entity mentions in text. Experiments on the public bAbI corpus (Bordes et al., 2017) have shown that HCNs can reduce the number of training dialogs required by an order of magnitude compared to state-of-the-art end-to-end learning methods which do not employ domain knowledge. This demonstration shows a practical implementation of HCNs, as a web service for building task-oriented dialog systems. Once the developer has provided their domain-specific software, they can add training dialogs in several ways. First, the developer can simply upload dialogs to the training set. Second, the developer can interactively teach the HCN, and making on-the-spot corrections. Finally, as the HCN interacts with endusers, the developer can inspect logged dialogs, make corrections if needed, and add the dialogs to the training set. The next section describes the architecture and operation of the platform, and the final section describes how the developer uses the service – i.e., what the demonstration shows.