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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Weihao, He, Keqing, Wang, Yejie, Fu, Dayuan, Xu, Weiran
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910350652211200
author Zeng, Weihao
He, Keqing
Wang, Yejie
Fu, Dayuan
Xu, Weiran
author_facet Zeng, Weihao
He, Keqing
Wang, Yejie
Fu, Dayuan
Xu, Weiran
contents 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 framework. Unlike contrastive counterparts, BootTOD aligns context and context+response representations and dismisses the requirements of contrastive pairs. BootTOD also uses multiple appropriate response targets to model the intrinsic one-to-many diversity of human conversations. Experimental results show that BootTOD outperforms strong TOD baselines on diverse downstream dialogue tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01163
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
Zeng, Weihao
He, Keqing
Wang, Yejie
Fu, Dayuan
Xu, Weiran
Computation and Language
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 framework. Unlike contrastive counterparts, BootTOD aligns context and context+response representations and dismisses the requirements of contrastive pairs. BootTOD also uses multiple appropriate response targets to model the intrinsic one-to-many diversity of human conversations. Experimental results show that BootTOD outperforms strong TOD baselines on diverse downstream dialogue tasks.
title BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
topic Computation and Language
url https://arxiv.org/abs/2403.01163