no code implementations • COLING 2022 • Jinfeng Zhou, Bo wang, Zhitong Yang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
In CRS, implicit patterns of user interest sequence guide the smooth transition of dialog utterances to the goal item.
no code implementations • COLING 2022 • Zhitong Yang, Bo wang, Jinfeng Zhou, Yue Tan, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
We design a global reinforcement learning with the planned paths to flexibly adjust the local response generation model towards the global target.
no code implementations • 23 Dec 2022 • Zhitong Yang, Xing Ma, Anqi Liu, Zheyu Zhang
Task-oriented dialog(TOD) aims to assist users in achieving specific goals through multi-turn conversation.