arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.08860cs.CL

规划、生成与复杂化:通过由易到难的零样本数据增强改进低资源对话状态追踪

Plan, Generate and Complicate: Improving Low-resource Dialogue State Tracking via Easy-to-Difficult Zero-shot Data Augmentation

School of Computer Science and Technology, East China Normal University(华东师范大学计算机科学与技术学院)

Ming Gu, Yan Yang

AI总结:

本文提出 EDZ-DA 框架,利用大语言模型按领域关系进行由易到难的零样本对话数据增强,并通过复杂化对话和槽位值排列提升低资源对话状态追踪性能,在 MultiWOZ 上优于已有基线。

摘要:

数据增强方法一直是提升低资源对话状态追踪中小模型性能的一个有前景的方向。然而,传统方法依赖预定义的用户目标,并忽视了数据复杂度在该任务中的重要性。本文提出 EDZ-DA,一个面向低资源对话状态追踪的由易到难零样本数据增强框架,该框架利用大语言模型自动捕捉不同领域之间的关系,然后生成对话数据。我们还基于领域关系对对话进行复杂化处理,以增强模型在共指槽位追踪方面的能力。此外,我们对槽位值进行排列,以减轻输出顺序的影响以及值生成不完整的问题。实验结果表明,与 MultiWOZ 上先前强大的数据增强基线相比,我们提出的方法具有优越性。

英文摘要:

Data augmentation methods have been a promising direction to improve the performance of small models for low-resource dialogue state tracking. However, traditional methods rely on pre-defined user goals and neglect the importance of data complexity in this task. In this paper, we propose EDZ-DA, an Easy-to-Difficult Zero-shot Data Augmentation framework for low-resource dialogue state tracking that utilizes large language models to automatically catch the relationships of different domains and then generate the dialogue data. We also complicate the dialogues based on the domain relation to enhance the model's capability for co-reference slot tracking. Furthermore, we permute slot values to mitigate the influence of output orders and the problem of incomplete value generation. Experimental results illustrate the superiority of our proposed method compared to previous strong data augmentation baselines on MultiWOZ.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑