Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
arXiv:2010.00910
Abstract
Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a "continual learning" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a method called ARPER (Adaptively Regularized Prioritized Exemplar Replay) by replaying prioritized historical exemplars, together with an adaptive regularization technique based on ElasticWeight Consolidation. Extensive experiments to continually learn new domains and intents are conducted on MultiWoZ-2.0 to benchmark ARPER with a wide range of techniques. Empirical results demonstrate that ARPER significantly outperforms other methods by effectively mitigating the detrimental catastrophic forgetting issue.
Accepted as Long Paper at "Findgins of EMNLP, 2020"
References in corpus (9)
- Distilling the Knowledge in a Neural Network
- Overcoming catastrophic forgetting in neural networks
- Improving neural networks by preventing co-adaptation of feature detectors
- Continual Learning Through Synaptic Intelligence
- Measuring Catastrophic Forgetting in Neural Networks
- Learning and Evaluating General Linguistic Intelligence
- Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
- Toward Continual Learning for Conversational Agents
- Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems