Transfer Fine-Tuning: A BERT Case Study

Yuki Arase, Jun’ichi Tsujii


Abstract
A semantic equivalence assessment is defined as a task that assesses semantic equivalence in a sentence pair by binary judgment (i.e., paraphrase identification) or grading (i.e., semantic textual similarity measurement). It constitutes a set of tasks crucial for research on natural language understanding. Recently, BERT realized a breakthrough in sentence representation learning (Devlin et al., 2019), which is broadly transferable to various NLP tasks. While BERT’s performance improves by increasing its model size, the required computational power is an obstacle preventing practical applications from adopting the technology. Herein, we propose to inject phrasal paraphrase relations into BERT in order to generate suitable representations for semantic equivalence assessment instead of increasing the model size. Experiments on standard natural language understanding tasks confirm that our method effectively improves a smaller BERT model while maintaining the model size. The generated model exhibits superior performance compared to a larger BERT model on semantic equivalence assessment tasks. Furthermore, it achieves larger performance gains on tasks with limited training datasets for fine-tuning, which is a property desirable for transfer learning.
Anthology ID:
D19-1542
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5393–5404
Language:
URL:
https://aclanthology.org/D19-1542
DOI:
10.18653/v1/D19-1542
Bibkey:
Cite (ACL):
Yuki Arase and Jun’ichi Tsujii. 2019. Transfer Fine-Tuning: A BERT Case Study. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5393–5404, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Transfer Fine-Tuning: A BERT Case Study (Arase & Tsujii, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1542.pdf
Code
 yukiar/TransferFT