Task-oriented dialogue (TOD) systems are mainly based on the slot-filling-based TOD (SF-TOD) framework, in which dialogues are broken down into smaller, controllable units (i.e., slots) to fulfill a specific task. A series of approaches based on this framework achieved remarkable success on various TOD benchmarks. However, we argue that the current TOD benchmarks are limited to surrogate real-world scenarios and that the current TOD models are still a long way to cover the scenarios. In this position paper, we first identify current status and limitations of SF-TOD systems. After that, we explore the WebTOD framework, the alternative direction for building a scalable TOD system when a web/mobile interface is available. In WebTOD, the dialogue system learns how to understand the web/mobile interface that the human agent interacts with, powered by a large-scale language model.
@article{arxiv.2212.10504,
title = {Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?},
author = {Sang-Woo Lee and Sungdong Kim and Donghyeon Ko and Donghoon Ham and Youngki Hong and Shin Ah Oh and Hyunhoon Jung and Wangkyo Jung and Kyunghyun Cho and Donghyun Kwak and Hyungsuk Noh and Woomyoung Park},
journal= {arXiv preprint arXiv:2212.10504},
year = {2023}
}