This challenge provides a partial conversation, and requires participants to select the correct next utterances from a set of candidates. Unlike previous similar challenges, this task tries to push towards real world problems by introducing:
- A large number of candidates
- Cases where no candidate is correct
- External data
This challenge is offered with two goal oriented dialog datasets, used in 5 tasks. A participant may participate in one, several, or all the subtasks.
For more detail, please visit our website.
Lazaros Polymenakos, Chulaka Gunasekara – IBM Research AI
Walter Lasecki, Jonathan K. Kummerfeld – University of Michigan