# Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining

arXiv: https://arxiv.org/abs/2003.13003 · HTML: https://mlsanity.com/paper/2003.13003/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2020.

## Built on by (most cited first, 6 of 6)

- [UDALM: Unsupervised Domain Adaptation through Language Modeling](https://mlsanity.com/paper/2104.07078/) (2021)
- [On the Interplay Between Fine-tuning and Composition in Transformers](https://mlsanity.com/paper/2105.14668/) (2021)
- [HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression](https://mlsanity.com/paper/2110.08551/) (2021)
- [TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification](https://mlsanity.com/paper/2308.15010/) (2023)
- [Finding Pragmatic Differences Between Disciplines](https://mlsanity.com/paper/2310.00204/) (2023)
- [Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding](https://mlsanity.com/paper/2311.06761/) (2023)

## Abstract (arXiv)

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.