A Wizard-of-Oz Study on A Non-Task-Oriented Dialog Systems That Reacts to User Engagement
نویسندگان
چکیده
In this paper, we describe a system that reacts to both possible system breakdowns and low user engagement with a set of conversational strategies. These general strategies reduce the number of inappropriate responses and produce better user engagement. We also found that a system that reacts to both possible system breakdowns and low user engagement is rated by both experts and non-experts as having better overall user engagement compared to a system that only reacts to possible system breakdowns. We argue that for non-task-oriented systems we should optimize on both system response appropriateness and user engagement. We also found that apart from making the system response appropriate, funny and provocative responses can also lead to better user engagement. On the other hand, short appropriate responses, such as “Yes” or “No” can lead to decreased user engagement. We will use these findings to further improve our system.
منابع مشابه
Out-of-Domain Spoken Dialogs in the Car: A WoZ Study
Mobile Internet access via smartphones puts demands on in-car infotainment systems, as more and more drivers like to access the Internet while driving. Spoken dialog systems (SDS) distract drivers less than visual/haptic-based dialog systems. However, in conversational SDSs drivers might speak utterances which are not in the domain of the SDS and thus cannot be understood. In a Wizard of Oz stu...
متن کاملIn-Car Multi-Domain Spoken Dialogs: A Wizard of Oz Study
Mobile Internet access via smartphones puts demands on in-car infotainment systems, as more and more drivers like to access the Internet while driving. Spoken dialog systems support the user by less distracting interaction than visual/hapticbased dialog systems. To develop an intuitive and usable spoken dialog system, an extensive analysis of the interaction concept is necessary. We conducted a...
متن کاملDifferences in User Responses to a Wizard-of-Oz versus Automated System
Wizard-of-Oz experimental setup in a dialogue system is commonly used to gather data for informing an automated version of that system. Previous work has exposed dependencies between user behavior towards systems and user belief about whether the system is automated or human-controlled. This work examines whether user behavior changes when user belief is held constant and the system’s operator ...
متن کاملBehavior models for learning and receptionist dialogs
We present a dialog model for identifying persons, learning person names, and associated face IDs in a receptionist dialog. The proposed model allows a decomposition of the main dialog task into separate dialog behaviors which can be implemented separately and allow a mixture of handcrafted models and dialog strategies trained with reinforcement learning. The dialog model was implemented on our...
متن کاملFish or Fowl: A Wizard of Oz Evaluation of Dialogue Strategies in the Restaurant Domain
Recent work on evaluation of spoken dialogue systems suggests that the information presentation phase of complex dialogues is often the primary contributor to dialogue duration. This indicates that better algorithms are needed for the presentation of complex information in speech. Currently however we lack data about the tasks and dialogue strategies on which to base such algorithms. In this pa...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016