A Network-based End-to-End Trainable Task-oriented Dialogue System
This work addresses the problem of simplifying development for task-oriented dialogue systems, which typically require complex, multi-component setups with extensive handcrafting or costly labeled data, though it appears incremental as it builds on existing neural and data collection approaches.
The authors tackled the challenge of building task-oriented dialogue systems by introducing an end-to-end trainable neural network model that operates on text input and output, along with a new data collection method using a pipelined Wizard-of-Oz framework. The results demonstrate that the model can converse naturally with humans to help accomplish tasks in a restaurant search domain.
Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework. This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand. The results show that the model can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.