1 code implementation • 5 Jun 2023 • Lvxiaowei Xu, Jianwang Wu, Jiawei Peng, Zhilin Gong, Ming Cai, Tianxiang Wang
We adopt usage-based construction grammar as the basis of our work, which is highly compatible with statistical models such as PLMs.
no code implementations • 27 Feb 2023 • Shuo Zhang, Junzhou Zhao, Pinghui Wang, Tianxiang Wang, Zi Liang, Jing Tao, Yi Huang, Junlan Feng
To cope with this problem, we explore to improve multi-action dialog policy learning with explicit and implicit turn-level user feedback received for historical predictions (i. e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios.