Saved in:
Bibliographic Details
Main Authors: Liu, Zequn, Zhang, Ruiyi, Song, Yiping, Ju, Wei, Zhang, Ming
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2005.11700
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910419769098240
author Liu, Zequn
Zhang, Ruiyi
Song, Yiping
Ju, Wei
Zhang, Ming
author_facet Liu, Zequn
Zhang, Ruiyi
Song, Yiping
Ju, Wei
Zhang, Ming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2005_11700
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications
Liu, Zequn
Zhang, Ruiyi
Song, Yiping
Ju, Wei
Zhang, Ming
Computation and Language
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.
title When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications
topic Computation and Language
url https://arxiv.org/abs/2005.11700