Conversation Learner -- A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems
This addresses the problem of creating efficient dialog systems for industry applications by offering a tool that reduces data requirements and enhances flexibility, though it is incremental in combining existing methods.
The paper tackles the challenge of building flexible yet interpretable dialog managers for task-oriented systems by introducing Conversation Learner, a machine teaching tool that converts rule-based dialog flows into parametric models and improves them using dialog logs, resulting in a hybrid approach that balances performance and transparency.
Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows. While dialog flows are intuitively interpretable and good for simple scenarios, they fall short of performance in terms of the flexibility needed to handle complex dialogs. On the other hand, purely machine-learned models can handle complex dialogs, but they are considered to be black boxes and require large amounts of training data. In this demonstration, we showcase Conversation Learner, a machine teaching tool for building dialog managers. It combines the best of both approaches by enabling dialog authors to create a dialog flow using familiar tools, converting the dialog flow into a parametric model (e.g., neural networks), and allowing dialog authors to improve the dialog manager (i.e., the parametric model) over time by leveraging user-system dialog logs as training data through a machine teaching interface.