no code implementations • 3 Jan 2023 • Mingzhe Li, Xiuying Chen, Weiheng Liao, Yang song, Tao Zhang, Dongyan Zhao, Rui Yan
The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource.