Papers with DAML
Low Resource Style Transfer via Domain Adaptive Meta Learning (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing unsupervised text style transfer methods suffer from performance degradation when fine-tuning the model in new domains. |
| Approach: | They propose a domain adaptive meta-learning approach with an adversarial style training approach for better content preservation and style transfer. |
| Outcome: | The proposed approach generalizes well on unseen low-resource domains against ten strong baselines. |
Domain Adaptive Dialog Generation via Meta Learning (P19-1)
Copied to clipboard
| Challenge: | Existing methods to adapt dialog data to new domains with limited resources are expensive . a domain adaptive dialog system model learns from multiple rich-resource tasks and adapts to new tasks with minimal training samples. |
| Approach: | They propose a domain adaptive dialog generation method based on meta-learning . they train a dialog system model using multiple rich-resource single-domain dialog data . |
| Outcome: | The proposed method can learn a competitive dialog system on a new domain with minimal training examples. |