No abstract

Complex domains demand task-oriented dialog system (TODS) to be able to reason and engage with humans in dialog and in information retrieval. This may require contemporary dialog systems to have improved conversation handling capabilities. One stating point is supporting conversations which logically advances, such that they could be able to handle sub dialogs meant to elicit more information, within a topic. This paper presents some findings on the research that has been carried out by the authors with regard to highlighting this problem and suggesting a possible solution. A solution which intended to minimize heavy reliance on handcrafts which have varying challenges. The study discusses an experiment for evaluating a novel architecture envisioned to improve this conversational requirement. The experiment results clearly depict the extent to which we have achieved this desired progression, the underlying effects to users and the potential implications to application. The study recommends combining Agency and Reinforcement learning to deliver the solution and could guide future studies towards achieving even more natural conversations.

Recent handcrafts on dialog manager in task-oriented dialog systems (TODS) offer great promises on handling conversations. However, most tend to be shortsighted in handling advancing conversations. Modelling the future direction on conversations is crucial for TODS that can be scaled across multi-domain. This paper proposes a novel architectural model for the dialog manager, (MAS_DM). In this model, the dialog manager is a MAS. The architecture consists of multiple intelligent interacting agents, namely, state agent, master agent, and dialog agents. Each agent performs a set of tasks to achieve the overall goal of advancing the conversation within a topic. In this paper, the particular component of the Dialogue Manager, and Strategy selection has been discussed in detail. The notion of learning is essential, since it is intended to provide a means to which the agents will adapt to their environment. We show how to combine MAS and RL to enable agents learn a topic of interest and support an advancing conversation on the same. This will enable the realization of advancing conversations between a human and the TODS on a given topic.