Abstract
Recurrent Neural Networks (RNNs) have achieved tremendous success in sequential data processing. However, it is quite challenging to interpret and verify RNNs’ behaviors directly. To this end, many efforts have been made to extract finite automata from RNNs. Existing approaches such as exact learning are effective in extracting finite-state models to characterize the state dynamics of RNNs for formal languages, but are limited in the scalability to process natural languages. Compositional approaches that are scablable to natural languages fall short in extraction precision. In this paper, we identify the transition sparsity problem that heavily impacts the extraction precision. To address this problem, we propose a transition rule extraction approach, which is scalable to natural language processing models and effective in improving extraction precision. Specifically, we propose an empirical method to complement the missing rules in the transition diagram. In addition, we further adjust the transition matrices to enhance the context-aware ability of the extracted weighted finite automaton (WFA). Finally, we propose two data augmentation tactics to track more dynamic behaviors of the target RNN. Experiments on two popular natural language datasets show that our method can extract WFA from RNN for natural language processing with better precision than existing approaches. Our code is available at https://github.com/weizeming/Extract_WFA_from_RNN_for_NL.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdel-Hamid, O., Mohamed, A.R., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 22(10), 1533–1545 (2014)
Angluin, D.: Learning regular sets from queries and counterexamples. Inf. Comput. 75(2), 87–106 (1987)
Baier, C., Katoen, J.P.: Principles of Model Checking. MIT press (2008)
Cechin, A.L., Regina, D., Simon, P., Stertz, K.: State automata extraction from recurrent neural nets using k-means and fuzzy clustering. In: 23rd International Conference of the Chilean Computer Science Society, 2003. SCCC 2003. Proceedings, pp. 73–78. IEEE (2003)
Che, Z., Purushotham, S., Cho, K., Sontag, D., Liu, Y.: Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8(1), 1–12 (2018)
Datta, D., David, P.E., Mittal, D., Jain, A.: Neural machine translation using recurrent neural network. Int. J. Eng. Adv. Technol. 9(4), 1395–1400 (2020)
Dong, G., et al.: Towards interpreting recurrent neural networks through probabilistic abstraction. In: 2020 35th IEEE/ACM International Conference on Automated Software Engineering (ASE), pp. 499–510. IEEE (2020)
Du, X., Li, Y., Xie, X., Ma, L., Liu, Y., Zhao, J.: Marble: model-based robustness analysis of stateful deep learning systems. In: Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering, pp. 423–435 (2020)
Du, X., Xie, X., Li, Y., Ma, L., Liu, Y., Zhao, J.: Deepstellar: model-based quantitative analysis of stateful deep learning systems. In: Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 477–487 (2019)
Gastin, P., Monmege, B.: A unifying survey on weighted logics and weighted automata. Soft. Comput. 22(4), 1047–1065 (2015). https://doi.org/10.1007/s00500-015-1952-6
Goldberg, Y.: Neural network methods for natural language processing. Synth. Lect. Hum. Lang. Technol. 10(1), 1–309 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Jacobsson, H.: Rule extraction from recurrent neural networks: Ataxonomy and review. Neural Comput. 17(6), 1223–1263 (2005)
Jigsaw: Toxic comment classification challenge. https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge. Accessed 16 Apr 2022
Li, X., Roth, D.: Learning question classifiers. In: COLING 2002: The 19th International Conference on Computational Linguistics (2002)
Okudono, T., Waga, M., Sekiyama, T., Hasuo, I.: Weighted automata extraction from recurrent neural networks via regression on state spaces. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5306–5314 (2020)
Omlin, C.W., Giles, C.L.: Extraction of rules from discrete-time recurrent neural networks. Neural Netw. 9(1), 41–52 (1996)
Omlin, C.W., Giles, C.L.: Rule revision with recurrent neural networks. IEEE Trans. Knowl. Data Eng. 8(1), 183–188 (1996)
Omlin, C., Giles, C., Miller, C.: Heuristics for the extraction of rules from discrete-time recurrent neural networks. In: Proceedings 1992 IJCNN International Joint Conference on Neural Networks, vol. 1, pp. 33–38. IEEE (1992)
Powers, D.M.: Applications and explanations of zipf’s law. In: New Methods in Language Processing and Computational Natural Language Learning (1998)
Wang, Q., Zhang, K., Liu, X., Giles, C.L.: Verification of recurrent neural networks through rule extraction. arXiv preprint arXiv:1811.06029 (2018)
Wang, Q., Zhang, K., Ororbia, A.G., II., Xing, X., Liu, X., Giles, C.L.: An empirical evaluation of rule extraction from recurrent neural networks. Neural Comput. 30(9), 2568–2591 (2018)
Wang, R., Li, Z., Cao, J., Chen, T., Wang, L.: Convolutional recurrent neural networks for text classification. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2019)
Weiss, G., Goldberg, Y., Yahav, E.: Extracting automata from recurrent neural networks using queries and counterexamples. In: International Conference on Machine Learning, pp. 5247–5256. PMLR (2018)
Weiss, G., Goldberg, Y., Yahav, E.: Learning deterministic weighted automata with queries and counterexamples. 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/d3f93e7766e8e1b7ef66dfdd9a8be93b-Paper.pdf
Xie, X., et al.: Rnnrepair: automatic rnn repair via model-based analysis. In: International Conference on Machine Learning, pp. 11383–11392. PMLR (2021)
Zeng, Z., Goodman, R.M., Smyth, P.: Learning finite state machines with self-clustering recurrent networks. Neural Comput. 5(6), 976–990 (1993)
Zhang, X., Du, X., Xie, X., Ma, L., Liu, Y., Sun, M.: Decision-guided weighted automata extraction from recurrent neural networks. In: Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), pp. 11699–11707. AAAI Press (2021)
Acknowledgements
This research was sponsored by the National Natural Science Foundation of China under Grant No. 62172019, 61772038, and CCF-Huawei Formal Verification Innovation Research Plan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Wei, Z., Zhang, X., Sun, M. (2022). Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languages. In: Riesco, A., Zhang, M. (eds) Formal Methods and Software Engineering. ICFEM 2022. Lecture Notes in Computer Science, vol 13478. Springer, Cham. https://doi.org/10.1007/978-3-031-17244-1_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-17244-1_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17243-4
Online ISBN: 978-3-031-17244-1
eBook Packages: Computer ScienceComputer Science (R0)