When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications

arXiv:2005.11700v2 Announce Type: replace
Abstract: 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 …

abstract applications arxiv balance classification cs.cl data domain few-shot general language language generation language model low meta meta-learning model-agnostic nlp study tasks text text classification type work