Task Oriented Dialog System
Task-oriented dialog systems (TODS) aim to build conversational agents that efficiently complete user-specified tasks through natural language interaction. Current research emphasizes improving TODS robustness and efficiency by addressing data scarcity through techniques like data augmentation and semi-supervised learning, exploring novel model architectures such as retrieval-augmented generation and transformer-based models with adapters, and developing more effective user simulators. These advancements are crucial for creating more accurate, adaptable, and scalable TODS with broad applications in customer service, information retrieval, and other domains.
Papers
Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog
Haipeng Sun, Junwei Bao, Youzheng Wu, Xiaodong He
Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems
Weihao Zeng, Keqing He, Zechen Wang, Dayuan Fu, Guanting Dong, Ruotong Geng, Pei Wang, Jingang Wang, Chaobo Sun, Wei Wu, Weiran Xu
A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems
Hong Liu, Yucheng Cai, Zhijian Ou, Yi Huang, Junlan Feng
SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation
Wanwei He, Yinpei Dai, Min Yang, Jian Sun, Fei Huang, Luo Si, Yongbin Li
SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding
Wanwei He, Yinpei Dai, Binyuan Hui, Min Yang, Zheng Cao, Jianbo Dong, Fei Huang, Luo Si, Yongbin Li