Goal-Oriented Dialogue Policy Learning from Failures

A Goal Oriented Model Of Human Dialogue

Building Effective Goal-Oriented Dialogue Agents

Recent progress has seen an explosion in dialog systems, including voice-activated bots, text-based chatbots, and email-based bots for scheduling meetings. However real life interaction with these so-called intelligent agents consistently fall short of expectations. Consequently, this project deploys neural-based bots and rule-based bots across a wide variety of tasks in order to analyze where ...

Goal-Oriented Multimedia Dialogue with Variable Initiative

A dialogue algorithm is described that executes Prolog-style rules in an attempt to achieve a goal. The algorithm selects paths in the proof in an attempt to achieve success and proves subgoals on the basis of internally available information where possible. Where \missing axioms" are discovered, the algorithm interacts with the user to solve subgoals, and it uses the received information from ...

End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient

Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog transcripts between customers and trained human agents, encoder-decoder methods have gained popularity as agent utterances can be directly treated as supervision without the need f...

Learning Policy Constraints Through Dialogue

An understanding of the policy and resource availability constraints under which others operate is important for effectively developing and resourcing plans in a multi-agent context. Such constraints (or norms) are not necessarily public knowledge, even within a team of collaborating agents. What is required are mechanisms to enable agents to keep track of who might have and be willing to provi...