Incrementalizing RASA's Open-Source Natural Language Understanding Pipeline
This work addresses the need for incremental processing in dialogue systems, but it is incremental as it adapts an existing framework to a new processing mode.
The authors modified the open-source RASA natural language understanding pipeline to process text incrementally (word-by-word), enabling it to function effectively as an incremental service, as demonstrated by evaluations on the Snips dataset.
As spoken dialogue systems and chatbots are gaining more widespread adoption, commercial and open-sourced services for natural language understanding are emerging. In this paper, we explain how we altered the open-source RASA natural language understanding pipeline to process incrementally (i.e., word-by-word), following the incremental unit framework proposed by Schlangen and Skantze. To do so, we altered existing RASA components to process incrementally, and added an update-incremental intent recognition model as a component to RASA. Our evaluations on the Snips dataset show that our changes allow RASA to function as an effective incremental natural language understanding service.