Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks
arXiv:1908.10423
Abstract
Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust representations. However, these methods can achieve sub-optimal performance in low-resource scenarios. Inspired by the recent success of optimization-based meta-learning algorithms, in this paper, we explore the model-agnostic meta-learning algorithm (MAML) and its variants for low-resource NLU tasks. We validate our methods on the GLUE benchmark and show that our proposed models can outperform several strong baselines. We further empirically demonstrate that the learned representations can be adapted to new tasks efficiently and effectively.
arXiv commentEMNLP 2019
References in corpus (9)
- Distributed Representations of Words and Phrases and their Compositionality
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Natural Language Processing (almost) from Scratch
- Distributed Representations of Sentences and Documents
- Skip-Thought Vectors
- On First-Order Meta-Learning Algorithms
- Semi-supervised Sequence Learning
- Multi-Task Deep Neural Networks for Natural Language Understanding
- Multi-task Sequence to Sequence Learning