arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.09857cs.CL
收藏

TaSL:通过任务技能定位与巩固实现持续对话状态跟踪

TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation

The Hong Kong Polytechnic University(香港理工大学);Peking University(北京大学)

Yujie Feng, Xu Chu, Yongxin Xu, Guangyuan Shi, Bo Liu, Xiao-Ming Wu

AI总结:

提出TaSL框架,通过分组技术定位任务特定与共享区域,并利用细粒度技能巩固策略实现双向知识转移,在不依赖记忆回放的前提下有效缓解灾难性遗忘,在持续对话状态跟踪任务上显著超越现有最先进方法。

摘要:

实用的对话系统需要持续获取技能的能力以及对新任务的适应性,同时保留先验知识。然而,当前持续对话状态跟踪(DST)方法作为对话系统的关键功能,在应对灾难性遗忘问题及任务间的知识转移方面仍存在困难。我们提出了TaSL,一个用于任务技能定位与巩固的新框架,它无需依赖记忆回放即可实现有效的知识转移。TaSL采用一种新颖的分组技术来精确定位任务特定和任务共享区域。此外,一种细粒度的技能巩固策略在更新共享知识以实现双向知识转移的同时,保护任务特定知识免遭遗忘。因此,TaSL在保留先验知识与擅长新任务之间取得了平衡。在多种骨干网络上的综合实验凸显了TaSL相比现有最先进方法的显著性能提升。提供了源代码以确保可复现性。

英文摘要:

A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks. We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay. TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas. Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer. As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks. Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL over existing state-of-the-art methods. The source code is provided for reproducibility.

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。

↑