Building Effective Goal-Oriented Dialogue Agents
نویسنده
چکیده
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 the behavior between the systems differ. We find that even without excessive handcrafted logic, rules-based methods can manage to perform on par with neural-based methods. Based on these results, we pinpoint strategic areas of improvement for neural-based goal-oriented dialog agents.
منابع مشابه
Analysis of Listening-Oriented Dialogue for Building Listening Agents
Our aim is to build listening agents that can attentively listen to the user and satisfy his/her desire to speak and have himself/herself heard. This paper investigates the characteristics of such listening-oriented dialogues so that such a listening process can be achieved by automated dialogue systems. We collected both listening-oriented dialogues and casual conversation, and analyzed them b...
متن کاملTask-Oriented Tutorial Dialogue: Issues and Agents
Towards our goal of developing computer tutors that can collaborate with students on tasks in simulated environments, we have built a series of four prototype tutors. These tutors integrate two independent but related strands of research: intelligent tutoring systems and task-oriented dialogue systems. While the tutors share a core approach to teaching procedural tasks, each was designed to exp...
متن کاملModelization and experimentation of conversational policies for non task oriented agents based on dissonance and relevance theories
We propose a model for dialogue between non task oriented agents, based on the dissonance and relevance theories. Non task oriented agents are studied as a model for non expert agents, as opposed to task oriented agents, in order to provide models for social science simulations. Dialogue between non task oriented agents can not be modelled like task oriented dialogue because no criterium is pro...
متن کاملDisfluent but effective? A quantitative study of disfluencies and conversational moves in team discourse
Situated dialogue systems that interact with humans as part of a team (e.g., robot teammates) need to be able to use information from communication channels to gauge the coordination level and effectiveness of the team. Currently, the feasibility of this end goal is limited by several gaps in both the empirical and computational literature. The purpose of this paper is to address those gaps in ...
متن کاملEvaluation of Listening-Oriented Dialogue Control Rules Based on the Analysis of HMMs
We have been working on listening-oriented dialogues for the purpose of building listening agents. In our previous work [1], we trained hidden Markov models (HMMs) from listeningoriented dialogues (LoDs) between humans, and by analyzing them, discovered a distinguishing dialogue flow of LoD. For example, listeners suppress their information giving and selfdisclosure, and instead, increase ackno...
متن کامل