MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation

1 code implementation • 22 May 2023 • Jia-Chen Gu, Chao-Hong Tan, Caiyuan Chu, Zhen-Hua Ling, Chongyang Tao, Quan Liu, Cong Liu

Given an MPC with a few addressee labels missing, existing methods fail to build a consecutively connected conversation graph, but only a few separate conversation fragments instead.

Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction

no code implementations • 9 Mar 2023 • Caiyuan Chu, Ya Li, Yifan Liu, Jia-Chen Gu, Quan Liu, Yongxin Ge, Guoping Hu

The key to automatic intention induction is that, for any given set of new data, the sentence representation obtained by the model can be well distinguished from different labels.

Clustering Contrastive Learning +3