When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications
This provides insights for researchers and practitioners using MAML in NLP, but it is incremental as it builds on existing methods without introducing new ones.
The paper tackles the problem of understanding when Model-Agnostic Meta-Learning (MAML) performs best in NLP applications by empirically studying factors like data quantity and task similarity, concluding with guidelines based on experimental results.
Model-Agnostic Meta-Learning (MAML), a model-agnostic meta-learning method, is successfully employed in NLP applications including few-shot text classification and multi-domain low-resource language generation. Many impacting factors, including data quantity, similarity among tasks, and the balance between general language model and task-specific adaptation, can affect the performance of MAML in NLP, but few works have thoroughly studied them. In this paper, we conduct an empirical study to investigate these impacting factors and conclude when MAML works the best based on the experimental results.