Abstract
Large pre-trained models like BERT and RoBERTa have gained massive popularity as they have surpassed previous state-of-the-art models in various Natural Language Processing (NLP) tasks. Nevertheless, interpreting their behavior is still an ongoing challenge as these models are composed of millions of parameters. The introduction of the Fuzzy Fingerprint (FFP) framework provided a straightforward classification technique able to deliver result interpretations, however, this method was outperformed by these large pre-trained models. In this work, we introduce a novel method that combines the simplicity of the FFPs with the ability to detect complex patterns of large pre-trained models, in order to build a more interpretable classification framework. Furthermore, we show that it is feasible to obtain unique FFPs for each label that enable the examination of incorrect classifications. We evaluate our new method on four text classification benchmark datasets and show that it is possible to gain interpretability without any noticeable loss in performance.
Supported by Fundação para a Ciência e a Tecnologia (FCT), through Portuguese national funds Ref. UIDB/50021/2020, Agência Nacional de Inovação (ANI), through the projects CMU-PT MAIA Ref. 045909, Plano de Recuperação e Resiliência (PRR) Center for Responsible AI C645008882-00000055, and the COST Action Multi3Generation Ref. CA18231.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
FFP should not be confused with the identically named work by Stein et al. [9].
- 2.
- 3.
References
Ghosal, D., Majumder, N., Gelbukh, A., Mihalcea, R., Poria, S.: Cosmic: commonsense knowledge for emotion identification in conversations. arXiv preprint arXiv:2010.02795 (2020)
Homem, N., Carvalho, J.P.: Authorship identification and author fuzzy “fingerprints”. In: 2011 Annual Meeting of the North American Fuzzy Information Processing Society, pp. 1–6. IEEE (2011)
Homem, N., Carvalho, J.P.: Web user identification with fuzzy fingerprints. In: 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011), pp. 2622–2629. IEEE (2011)
Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)
Li, J., Lin, Z., Fu, P., Wang, W.: Past, present, and future: conversational emotion recognition through structural modeling of psychological knowledge. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 1204–1214 (2021)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019). http://arxiv.org/abs/1907.11692
Rosa, H., Batista, F., Carvalho, J.P.: Twitter topic fuzzy fingerprints. In: 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 776–783. IEEE (2014)
Shen, W., Chen, J., Quan, X., Xie, Z.: DialogXL: all-in-one XLNet for multi-party conversation emotion recognition. arXiv preprint arXiv:2012.08695 (2020)
Stein, B.: Fuzzy-fingerprints for text-based information retrieval. In: Proceedings of the 5th International Conference on Knowledge Management (I-KNOW 2005), Graz, Journal of Universal Computer Science, pp. 572–579. Citeseer (2005)
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
Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)
Xie, Q., Dai, Z., Hovy, E., Luong, T., Le, Q.: Unsupervised data augmentation for consistency training. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6256–6268 (2020)
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: XLNet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ribeiro, R., Pereira, P., Coheur, L., Moniz, H., Carvalho, J.P. (2023). Fuzzy Fingerprinting Large Pre-trained Models. In: Massanet, S., Montes, S., Ruiz-Aguilera, D., González-Hidalgo, M. (eds) Fuzzy Logic and Technology, and Aggregation Operators. EUSFLAT AGOP 2023 2023. Lecture Notes in Computer Science, vol 14069. Springer, Cham. https://doi.org/10.1007/978-3-031-39965-7_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-39965-7_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39964-0
Online ISBN: 978-3-031-39965-7
eBook Packages: Computer ScienceComputer Science (R0)