Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Model
This addresses robustness in spoken dialog systems for noisy inputs, but is incremental as it builds on prior challenge tasks.
The paper tackled adapting document-grounded dialog systems to noisy ASR transcripts in spoken conversations, achieving 1st rank in automatic and 3rd in human evaluations in a challenge.
This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations". Similar to the previous year's iteration, the task consists of three subtasks: detecting whether a turn is knowledge seeking, selecting the relevant knowledge document and finally generating a grounded response. This year, the focus lies on adapting the system to noisy ASR transcripts. We explore different approaches to make the models more robust to this type of input and to adapt the generated responses to the style of spoken conversations. For the latter, we get the best results with a noisy channel model that additionally reduces the number of short and generic responses. Our best system achieved the 1st rank in the automatic and the 3rd rank in the human evaluation of the challenge.