Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining
arXiv:2003.13003
Abstract
Pre-trained neural language models bring significant improvement for various NLP tasks, by fine-tuning the models on task-specific training sets. During fine-tuning, the parameters are initialized from pre-trained models directly, which ignores how the learning process of similar NLP tasks in different domains is correlated and mutually reinforced. In this paper, we propose an effective learning procedure named Meta Fine-Tuning (MFT), served as a meta-learner to solve a group of similar NLP tasks for neural language models. Instead of simply multi-task training over all the datasets, MFT only learns from typical instances of various domains to acquire highly transferable knowledge. It further encourages the language model to encode domain-invariant representations by optimizing a series of novel domain corruption loss functions. After MFT, the model can be fine-tuned for each domain with better parameter initializations and higher generalization ability. We implement MFT upon BERT to solve several multi-domain text mining tasks. Experimental results confirm the effectiveness of MFT and its usefulness for few-shot learning.
arXiv commentaccepted by emnlp 2020
References in corpus (11)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- A DIRT-T Approach to Unsupervised Domain Adaptation
- The Natural Language Decathlon: Multitask Learning as Question Answering
- Wasserstein Distance Guided Representation Learning for Domain Adaptation
- A Comprehensive Survey on Transfer Learning
- Multi-Task Deep Neural Networks for Natural Language Understanding
- Meta-Learning: A Survey
- BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
- StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
- Automated Relational Meta-learning
- Goal-Oriented Multi-Task BERT-Based Dialogue State Tracker