Towards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximization

arXiv:2403.10894v1 Announce Type: new
Abstract: In our dynamic world where data arrives in a continuous stream, continual learning enables us to incrementally add new tasks/domains without the need to retrain from scratch. A major challenge in continual learning of language model is catastrophic forgetting, the tendency of models to forget knowledge from previously trained tasks/domains when training on new ones. This paper studies dialog generation under the continual learning setting. We propose a novel method that 1) uses \textit{Text-Mixup} as …

abstract arxiv catastrophic forgetting challenge continual continuous cs.cl data dialog diversity domains dynamic language language model major norm nuclear robustness scratch tasks text type world