Multi-Domain Task-Completion Dialog Challenge

This challenge intends to foster progress in two important aspects of dialog systems: dialog complexity and scaling to new domains. First, there is an increasing interest in building complex bots that span over multiple sub-domains to accomplish a complex user goal such as travel planning which may include hotel, restaurant, attraction and so on. To advance state-of-the-art technologies for handling complex dialogs, we over a timely task focusing on multi-domain end-to-end task completion dialog. Second, neural dialog systems require very large datasets to learn to output consistent and grammatically-correct sentences. This makes it extremely hard to scale out the system to new domains with limited in-domain data. With this challenge, our goal is to investigate whether sample complexity can decrease with time, i.e., if a dialog system that was trained on a large corpus can learn to converse about a new domain given a much smaller in-domain corpus.