Skip to main content

How BERT’s Dropout Fine-Tuning Affects Text Classification?

  • 870 Accesses

Part of the Lecture Notes in Business Information Processing book series (LNBIP,volume 416)

Abstract

Language models pretraining facilitated fitting models on new and small datasets by keeping the previous pretraining knowledge. The task-agnostic models are to be fine-tuned on all NLP tasks. In this paper, we study the fine-tuning effect of BERT on small amount of data for news classification and sentiment analysis. Our experiments highlight the impact of tweaking the dropout hyper-parameters on the classification performance. We conclude that combining the hidden layers and the attention dropouts probabilities reduce overfitting.

Keywords

  • BERT
  • Fine-tuning
  • Text classification
  • Dropout

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-76508-8_11
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   84.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-76508-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   109.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.

Notes

  1. 1.

    http://groups.di.unipi.it/~gulli/AG_corpus_of_news_articles.html.

References

  1. Adhikari, A., Ram, A., Tang, R., Lin, J.: DocBERT: BERT for document classification. arXiv preprint arXiv:190408398 (2019)

  2. Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135–146 (2017)

    CrossRef  Google Scholar 

  3. Dai, A.M., Le, Q.V.: Semi-supervised sequence learning. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates Inc. (2015). https://proceedings.neurips.cc/paper/2015/file/7137debd45ae4d0ab9aa953017286b20-Paper.pdf

  4. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:181004805 (2018)

  5. Dodge, J., Ilharco, G., Schwartz, R., Farhadi, A., Hajishirzi, H., Smith, N.: Fine-tuning pretrained language models: weight initializations, data orders, and early stopping. arXiv preprint arXiv:200206305 (2020)

  6. Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 328–339. Association for Computational Linguistics, Melbourne (2018). https://doi.org/10.18653/v1/P18-1031. https://www.aclweb.org/anthology/P18-1031

  7. Huang, L., Ma, D., Li, S., Zhang, X., Wang, H.: Text level graph neural network for text classification. 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), pp. 3444–3450. Association for Computational Linguistics, Hong Kong (2019). https://doi.org/10.18653/v1/D19-1345. https://www.aclweb.org/anthology/D19-1345

  8. Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746–1751. Association for Computational Linguistics, Doha (2014). https://doi.org/10.3115/v1/D14-1181. https://www.aclweb.org/anthology/D14-1181

  9. Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. arXiv preprint arXiv:190911942 (2019)

  10. Lee, C., Cho, K., Kang, W.: Mixout: effective regularization to finetune large-scale pretrained language models. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=HkgaETNtDB

  11. Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:190711692 (2019)

  12. Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=Bkg6RiCqY7

  13. Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:13013781 (2013)

  14. Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)

    Google Scholar 

  15. Peters, M.E., et al.: Deep contextualized word representations. arXiv preprint arXiv:180205365 (2018)

  16. Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding with unsupervised learning (2018)

    Google Scholar 

  17. Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2383–2392. Association for Computational Linguistics, Austin (2016). https://doi.org/10.18653/v1/D16-1264. https://www.aclweb.org/anthology/D16-1264

  18. Sun, C., Qiu, X., Xu, Y., Huang, X.: How to fine-tune BERT for text classification? In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds.) CCL 2019. LNCS (LNAI), vol. 11856, pp. 194–206. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32381-3_16

    CrossRef  Google Scholar 

  19. Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:170603762 (2017)

  20. Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates Inc. (2019). https://proceedings.neurips.cc/paper/2019/file/dc6a7e655d7e5840e66733e9ee67cc69-Paper.pdf

  21. Zellers, R., Bisk, Y., Schwartz, R., Choi, Y.: SWAG: a large-scale adversarial dataset for grounded commonsense inference. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 93–104. Association for Computational Linguistics, Brussels (2018). https://doi.org/10.18653/v1/D18-1009. https://www.aclweb.org/anthology/D18-1009

  22. Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. arXiv preprint arXiv:150901626 (2015)

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Salma El Anigri .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

El Anigri, S., Himmi, M.M., Mahmoudi, A. (2021). How BERT’s Dropout Fine-Tuning Affects Text Classification?. In: Fakir, M., Baslam, M., El Ayachi, R. (eds) Business Intelligence. CBI 2021. Lecture Notes in Business Information Processing, vol 416. Springer, Cham. https://doi.org/10.1007/978-3-030-76508-8_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-76508-8_11

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-76507-1

  • Online ISBN: 978-3-030-76508-8

  • eBook Packages: Computer ScienceComputer Science (R0)