Emora STDM: A Versatile Framework for Innovative Dialogue System Development
This provides a versatile tool for researchers and developers building dialogue systems, though it appears incremental as it integrates existing approaches rather than introducing fundamentally new methods.
The authors introduced Emora STDM, a dialogue system development framework that combines state machine and information state approaches to enable rapid prototyping and collaborative development of dialogue managers. In a user study with interdisciplinary undergraduate students, the framework allowed both technical and non-technical students to develop creative dialogue managers quickly.
This demo paper presents Emora STDM (State Transition Dialogue Manager), a dialogue system development framework that provides novel workflows for rapid prototyping of chat-based dialogue managers as well as collaborative development of complex interactions. Our framework caters to a wide range of expertise levels by supporting interoperability between two popular approaches, state machine and information state, to dialogue management. Our Natural Language Expression package allows seamless integration of pattern matching, custom NLP modules, and database querying, that makes the workflows much more efficient. As a user study, we adopt this framework to an interdisciplinary undergraduate course where students with both technical and non-technical backgrounds are able to develop creative dialogue managers in a short period of time.