تقترح هذه الورقة تصنيفا من الأخطاء في أنظمة الحوار الموجهة للدردشة.سابقا، تم اقتراح اختصاصين؛واحد هو النظرية مدفوعة والبيانات الأخرى مدفوعة.السابق يعاني من حقيقة أن نظريات الحوار للمحادثة البشرية غالبا ما تكون مناسبة لتصنيف الأخطاء التي قدمها أنظمة الحوار الموجهة نحو الدردشة.هذا الأخير لديه قيود في أنه لا يمكن إلا أن يتعامل مع أخطاء النظم التي لدينا بيانات.تدمج هذه الورقة هذين تصنيفين لخلق تصنيف شامل للأخطاء في أنظمة الحوار الموجهة نحو الدردشة.وجدنا أنه، مع تصنيفنا المتكامل لدينا، يمكن تفاح أخطاء بشكل موثوق بموثوقية مع KAPPA أعلى من Fleiss 'Kappa مقارنة بالتصنيف المقترح سابقا.
This paper proposes a taxonomy of errors in chat-oriented dialogue systems. Previously, two taxonomies were proposed; one is theory-driven and the other data-driven. The former suffers from the fact that dialogue theories for human conversation are often not appropriate for categorizing errors made by chat-oriented dialogue systems. The latter has limitations in that it can only cope with errors of systems for which we have data. This paper integrates these two taxonomies to create a comprehensive taxonomy of errors in chat-oriented dialogue systems. We found that, with our integrated taxonomy, errors can be reliably annotated with a higher Fleiss' kappa compared with the previously proposed taxonomies.
References used
https://aclanthology.org/
Recent task-oriented dialogue systems learn a model from annotated dialogues, and such dialogues are in turn collected and annotated so that they are consistent with certain domain knowledge. However, in real scenarios, domain knowledge is subject to
Continual learning in task-oriented dialogue systems allows the system to add new domains and functionalities overtime after deployment, without incurring the high cost of retraining the whole system each time. In this paper, we propose a first-ever
Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many set-ups therefore rely on a user simulator instead of humans. These user
In goal-oriented dialogue systems, users provide information through slot values to achieve specific goals. Practically, some combinations of slot values can be invalid according to external knowledge. For example, a combination of cheese pizza'' (a
This paper aims at providing a comprehensive overview of recent developments in dialogue state tracking (DST) for task-oriented conversational systems. We introduce the task, the main datasets that have been exploited as well as their evaluation metr