Evaluating and Improving Continual Learning in Spoken Language Understanding

arXiv:2402.10427v1 Announce Type: new
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 concepts and evolving environments. The evaluation of continual learning algorithms typically involves assessing the model's stability, plasticity, and generalizability as fundamental aspects of standards. However, existing continual learning metrics primarily focus on only one or two of the properties. They neglect the overall performance across all …

abstract algorithms arxiv challenge concepts continual cs.ai cs.cl cs.sd emergence environments evaluation language language understanding slu spoken spoken language understanding stability tasks type understanding