FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue
Weihao Zeng, Keqing He, Yejie Wang, Chen Zeng, Jingang Wang, Yunsen Xian, Weiran Xu
Main: Dialogue and Interactive Systems Main-poster Paper
Poster Session 5: Dialogue and Interactive Systems (Poster)
Conference Room: Frontenac Ballroom and Queen's Quay
Conference Time: July 11, 16:15-17:45 (EDT) (America/Toronto)
Global Time: July 11, Poster Session 5 (20:15-21:45 UTC)
Keywords:
task-oriented
TLDR:
Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models less useful in practice. Current dialogue pre-training methods ...
You can open the
#paper-P766
channel in a separate window.
Abstract:
Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models less useful in practice. Current dialogue pre-training methods rely on a contrastive framework and face the challenges of both selecting true positives and hard negatives. In this paper, we propose a novel dialogue pre-training model, FutureTOD, which distills future knowledge to the representation of the previous dialogue context using a self-training framework. Our intuition is that a good dialogue representation both learns local context information and predicts future information. Extensive experiments on diverse downstream dialogue tasks demonstrate the effectiveness of our model, especially the generalization, robustness, and learning discriminative dialogue representations capabilities.