Past Challenges
DSTC1 (2012-2013)
Task: Dialog state tracking on human-computer dialogs in the bus timetable domain
Organizers: Jason D. Williams, Alan Black, Deepak Ramachandran, Antoine Raux
Venue: Special Session @ SIGDIAL 2013
DSTC2 (2013-2014)
Task: Dialog state tracking on human-computer dialogs in the restaurant information domain
Organizers: Matthew Henderson, Blaise Thomson, Jason D. Williams
Venue: Special Session @ SIGDIAL 2014
DSTC3 (2014)
Task: Domain adaptation for human-computer dialog state tracking from the restaurant to the tourist information domain
Organizers: Matthew Henderson, Blaise Thomson, Jason D. Williams
Venue: Special Session @ IEEE SLT 2014
DSTC4 (2015)
Task: Dialog state tracking on human-human dialogs in the tourist information domain
Organizers: Seokhwan Kim, Luis Fernando D’Haro, Rafael E. Banchs, Matthew Henderson, Jason D. Williams
Venue: Special Session @ IWSDS 2016
DSTC5 (2016)
Task: Cross-language dialog state tracking on human-human dialogs in the tourist information domain
Organizers: Seokhwan Kim, Luis Fernando D’Haro, Rafael E. Banchs, Matthew Henderson, Jason D. Williams, Koichiro Yoshino
Venue: Special Session @ IEEE SLT 2016
DSTC6 (2017)
Three Parallel Tracks
End-to-End Goal Oriented Dialog Learning: Task Description, Resources, Overview Paper
End-to-End Conversation Modeling: Task Description, Resources, Overview Paper
Dialogue Breakdown Detection: Task Description, Resources, Track Website, Overview Paper
Challenge Organizers: Chiori Hori, Julien Perez, Koichiro Yoshino, Seokhwan Kim
Venue: DSTC6 Workshop
DSTC7 (2018)
Three Parallel Tracks
Noetic End-to-End Response Selection: Task Description, Resources, Overview Paper
Grounded Response Generation: Task Description, Resources, Overview Paper
Audio Visual Scene-aware Dialog: Task Description, Resources, Overview Paper
Challenge Organizers: Koichiro Yoshino, Chiori Hori, Julien Perez, Luis Fernando D'Haro
Venue: DSTC7 Workshop @ AAAI-19
DSTC8 (2019)
Four Parallel Tracks
Multi-domain Task Completion: Task Description, Resources, Overview Paper
NOESIS II: Predicting Responses, Identifying Success, and Managing Complexity in Task-Oriented Dialogue: Task Description, Resources, Overview Paper
Audio Visual Scene-aware Dialog: Task Description, Resources, Overview Paper
Schema-Guided Dialogue State Tracking: Task Description, Resources, Overview Paper
Challenge Organizers: Seokhwan Kim, Michel Galley, Chulaka Gunasekara, Sungjin Lee
Venue: DSTC8 Workshop @ AAAI-20
DSTC9 (2020)
Four Parallel Tracks
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access: Task Description, Resources, Overview Paper
Multi-domain Task-oriented Dialog Challenge II: Task Description, Resources, Overview Paper
Interactive Evaluation of Dialog: Task Description, Resources, Overview Paper
SIMMC: Situated Interactive Multi-Modal Conversational AI: Task Description, Resources, Overview Paper
Challenge Organizers: Yun-Nung (Vivian) Chen, Chulaka Gunasekara, Luis Fernando D'Haro, Seokhwan Kim, Abhinav Rastogi
Venue: DSTC9 Workshop @ AAAI-21
DSTC10 (2021)
Five Parallel Tracks
MOD: Internet Meme Incorporated Open-domain Dialog: Task Description, Resources, Overview Paper
Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations: Task Description, Resources, Overview Paper
SIMMC 2.0: Situated Interactive Multimodal Conversational AI: Task Description, Resources, Overview Paper
Reasoning for Audio Visual Scene-Aware Dialog: Task Description, Resources, Overview Paper
Automatic Evaluation and Moderation of Open-domain Dialogue Systems: Task Description, Resources, Overview Paper
Challenge Organizers: Koichiro Yoshino, Yun-Nung (Vivian) Chen, Paul Crook, Satwik Kottur, Jinchao Li, Behnam Hedayatnia, Seungwhan (Shane) Moon