Abstract
Combining symbolic human knowledge with neural networks provides a rule-based ante-hoc explanation of the output. In this paper, we propose feature extracting functions for integrating human knowledge abstracted as logic rules into the predictive behaviour of a neural network. These functions are embodied as programming functions, which represent the applicable domain knowledge as a set of logical instructions and provide a modified distribution of independent features on input data. Unlike other existing neural logic approaches, the programmatic nature of these functions implies that they do not require any kind of special mathematical encoding, which makes our method very general and flexible in nature. We illustrate the performance of our approach for sentiment classification and compare our results to those obtained using two baselines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
References
Bach, S.H., Broecheler, M., Huang, B., Getoor, L.: Hinge-loss Markov random fields and probabilistic soft logic. CoRR abs/1505.04406 (2015)
Bach, S.H., et al.: Snorkel drybell: a case study in deploying weak supervision at industrial scale. In: Proceedings of the 2019 International Conference on Management of Data, pp. 362–375 (2019)
Gabbay, A., Garcez, A., Broda, K., Gabbay, D.M., Gabbay, P.: Neural-Symbolic Learning Systems: Foundations and Applications. Springer, London (2002). https://doi.org/10.1007/978-1-4471-0211-3
Ganchev, K., Graça, J., Gillenwater, J., Taskar, B.: Posterior regularization for structured latent variable models. J. Mach. Learn. Res. 11, 2001–2049 (2010)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 168–177 (2004)
Hu, Z., Ma, X., Liu, Z., Hovy, E., Xing, E.: Harnessing deep neural networks with logic rules. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany, pp. 2410–2420. Association for Computational Linguistics (2016)
Kim, Y.: Convolutional neural networks for sentence classification. CoRR abs/1408.5882 (2014)
Krishna, K., Jyothi, P., Iyyer, M.: Revisiting the importance of encoding logic rules in sentiment classification. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4743–4751 (2018)
Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. CoRR abs/1405.4053 (2014)
Lewis, D.D.: Feature selection and feature extraction for text categorization. In: Proceedings of the Workshop on Speech and Natural Language, pp. 212–217 (1992)
Liang, X., Hu, Z., Zhang, H., Lin, L., Xing, E.P.: Symbolic graph reasoning meets convolutions. In: Advances in Neural Information Processing Systems, pp. 1853–1863 (2018)
Nguyen, A.M., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. CoRR abs/1412.1897 (2014)
Pang, B., Lee, L.: Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales. In: Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL 2005) (2005)
Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., Zettlemoyer, L.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2227–2237 (2018)
Rai, A.: Explainable AI: from black box to glass box. J. Acad. Mark. Sci. 8(1), 137–141 (2020). https://doi.org/10.1007/s11747-019-00710-5
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?”: Explaining the predictions of any classifier. CoRR abs/1602.04938 (2016)
Szegedy, C., et al.: Intriguing properties of neural networks. In: International Conference on Learning Representations (2014)
Taskar, B., Guestrin, C., Koller, D.: Max-margin markov networks. In: NIPS, pp. 25–32 (2003)
Tran, S.N.: Unsupervised neural-symbolic integration. CoRR abs/1706.01991 (2017)
Vilone, G., Longo, L.: Explainable artificial intelligence: a systematic review. arXiv preprint arXiv:2006.00093 (2020)
Zeiler, M.D.: ADADELTA: an adaptive learning rate method. CoRR abs/1212.5701 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Gupta, S., Robles-Kelly, A., Bouadjenek, M.R. (2021). Feature Extraction Functions for Neural Logic Rule Learning. In: Torsello, A., Rossi, L., Pelillo, M., Biggio, B., Robles-Kelly, A. (eds) Structural, Syntactic, and Statistical Pattern Recognition. S+SSPR 2021. Lecture Notes in Computer Science(), vol 12644. Springer, Cham. https://doi.org/10.1007/978-3-030-73973-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-73973-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73972-0
Online ISBN: 978-3-030-73973-7
eBook Packages: Computer ScienceComputer Science (R0)
