Tracks

DSTC10 has the following five tracks (please click the links to get more detailed information about each track):

Track 1

MOD: Internet Meme Incorporated Open-domain Dialog

Task Proposal

Track Website

Test set data

Track 2

Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations

Task Proposal

Track Website

Test set data - task 1

Test set data - task 2

Track 3

SIMMC 2.0: Situated Interactive Multimodal Conversational AI

Task Proposal

Track Website

Track 4

Reasoning for Audio Visual Scene-Aware Dialog

Task Proposal

Track Website

Test set data

Submission site

Track 5

Automatic Evaluation and Moderation of Open-domain Dialogue Systems

Task Proposal

Track Website