Simplifying Dataflow Dialogue Design
This work aims to lower barriers for researchers in dialogue systems, though it is incremental as it builds on existing dataflow frameworks without introducing new methods.
The paper addresses the lack of community interest in dataflow-based dialogue systems by proposing a simplified annotation format and releasing an open-source execution engine to reduce perceived complexity.
In \citep{andreas2020task-oriented}, a dataflow (DF) based dialogue system was introduced, showing clear advantages compared to many commonly used current systems. This was accompanied by the release of SMCalFlow, a practically relevant, manually annotated dataset, more detailed and much larger than any comparable dialogue dataset. Despite these remarkable contributions, the community has not shown further interest in this direction. What are the reasons for this lack of interest? And how can the community be encouraged to engage in research in this direction? One explanation may be the perception that this approach is too complex - both the the annotation and the system. This paper argues that this perception is wrong: 1) Suggestions for a simplified format for the annotation of the dataset are presented, 2) An implementation of the DF execution engine is released\footnote{https://github.com/telepathylabsai/OpenDF}, which can serve as a sandbox allowing researchers to easily implement, and experiment with, new DF dialogue designs. The hope is that these contributions will help engage more practitioners in exploring new ideas and designs for DF based dialogue systems.