BriefGPT.xyz
Feb, 2024
评估和改进口语理解中的持续学习
Evaluating and Improving Continual Learning in Spoken Language Understanding
HTML
PDF
Muqiao Yang, Xiang Li, Umberto Cappellazzo, Shinji Watanabe, Bhiksha Raj
TL;DR
我们提出了一种评估方法,能够统一评估在连续学习中的稳定性、可塑性和泛化能力,并展示了引入不同的知识蒸馏方法如何改善语音语言理解模型的这三个性质方面。我们进一步展示了我们提出的指标更敏感地捕捉到连续学习中任务顺序的影响,因此更适合实际应用场景。
Abstract
continual learning
has emerged as an increasingly important challenge across various tasks, including
spoken language understanding
(SLU). In SLU, its objective is to effectively handle the emergence of new conce
→