BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses

arXiv:2403.01163v1 Announce Type: new
Abstract: Pre-trained language models have been successful in many scenarios. However, their usefulness in task-oriented dialogues is limited due to the intrinsic linguistic differences between general text and task-oriented dialogues. Current task-oriented dialogue pre-training methods rely on a contrastive framework, which faces challenges such as selecting true positives and hard negatives, as well as lacking diversity. In this paper, we propose a novel dialogue pre-training model called BootTOD. It learns task-oriented dialogue representations via a self-bootstrapping …

abstract arxiv bootstrap challenges cs.cl current dialogue differences diverse framework general intrinsic language language models pre-training responses text training true type