Abstract
The study of symbolic syntactic interpretations has been the cornerstone of natural language understanding for many years.
Today, modern artificial neural networks are widely searched to assess their syntactic ability, through several probing tasks.
In this paper, we propose a neural network system that explicitly includes syntactic interpretations: Kernel-inspired Encoder with Recursive Mechanism for Interpretable Trees Visualizer (KERMITviz). The most important result is that KERMITviz allows to visualize how syntax is used in inference. This system can be used in combination with transformer architectures like BERT, XLNet and clarifies the use of symbolic syntactic interpretations in specific neural networks making the black-box neural network neural networks explainable, interpretable and clear.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The code is available at https://github.com/ART-Group-it/KERMIT.
- 2.
References
Ancona, M., Ceolini, E., Öztireli, C., Gross, M.: Towards better understanding of gradient-based attribution methods for deep neural networks (2018)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), 1–46 (2015). https://doi.org/10.1371/journal.pone.0130140
Bien, J., Tibshirani, R.: Prototype selection for interpretable classification. Ann. Appl. Stat. 5(4) (2011). https://doi.org/10.1214/11-aoas495. http://dx.doi.org/10.1214/11-AOAS495
Collins, M., Duffy, N.: New ranking algorithms for parsing and tagging: kernels over discrete structures, and the voted perceptron. In: Proceedings of ACL 2002 (2002)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs/1810.0 (2018). http://arxiv.org/abs/1810.04805
Foster, Z.S.L., Sharpton, T.J., Grünwald, N.J.: Metacoder: an R package for visualization and manipulation of community taxonomic diversity data. PLoS Comput. Biol. 13(2) (2017). https://doi.org/10.1371/journal.pcbi.1005404
Hoover, B., Strobelt, H., Gehrmann, S.: exBERT: a visual analysis tool to explore learned representations in transformers models. arXiv e-prints arXiv:1910.05276, October 2019
Johnson, W., Lindenstrauss, J.: Extensions of Lipschitz mappings into a Hilbert space. Contemp. Math. 26, 189–206 (1984)
Kahng, M., Andrews, P.Y., Kalro, A., Chau, D.H.: ActiVis: visual exploration of industry-scale deep neural network models. CoRR abs/1704.01942 (2017). http://arxiv.org/abs/1704.01942
Liang, B., Yin, R., Gui, L., Du, J., He, Y., Xu, R.: Aspect-invariant sentiment features learning: Adversarial multi-task learning for aspect-based sentiment analysis. In: Proceedings of the 29th ACM International Conference on Information amp; Knowledge Management, CIKM 2020, New York, NY, USA, pp. 825–834. Association for Computing Machinery (2020). https://doi.org/10.1145/3340531.3411868
Ming, Y., et al.: Understanding hidden memories of recurrent neural networks. CoRR abs/1710.10777 (2017). http://arxiv.org/abs/1710.10777
Onorati, D., Tommasino, P., Ranaldi, L., Fallucchi, F., Zanzotto, F.M.: Pat-in-the-loop: declarative knowledge for controlling neural networks. Future Internet 12(12) (2020). https://doi.org/10.3390/fi12120218. https://www.mdpi.com/1999-5903/12/12/218
Plate, T.A.: Holographic reduced representations. IEEE Trans. Neural Networks 6(3), 623–641 (1995). https://doi.org/10.1109/72.377968
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should i trust you?”: explaining the predictions of any classifier (2016)
Rizos, G., Hemker, K., Schuller, B.: Augment to prevent: short-text data augmentation in deep learning for hate-speech classification. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM 2019, New York, NY, USA, pp. 991–1000. Association for Computing Machinery (2019). https://doi.org/10.1145/3357384.3358040
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vision 128(2), 336–359 (2019). https://doi.org/10.1007/s11263-019-01228-7. http://dx.doi.org/10.1007/s11263-019-01228-7
Shen, Y., Lin, Z., Huang, C.W., Courville, A.: Neural language modeling by jointly learning syntax and lexicon (2018)
Smilkov, D., Thorat, N., Nicholson, C., Reif, E., Viégas, F.B., Wattenberg, M.: Embedding projector: interactive visualization and interpretation of embeddings. arXiv preprint arXiv:1611.05469 (2016)
Strobelt, H., Gehrmann, S., Huber, B., Pfister, H., Rush, A.M.: Visual analysis of hidden state dynamics in recurrent neural networks. CoRR abs/1606.07461 (2016). http://arxiv.org/abs/1606.07461
Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)
Vig, J.: A multiscale visualization of attention in the transformer model. In: ACL 2019–57th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations, pp. 37–42 (2019)
Wallace, E., Tuyls, J., Wang, J., Subramanian, S., Gardner, M., Singh, S.: AllenNLP Interpret: a framework for explaining predictions of NLP models. In: Empirical Methods in Natural Language Processing (2019)
Wang, Y., Lee, H.Y., Chen, Y.N.: Tree transformer: integrating tree structures into self-attention. 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), Hong Kong, China, pp. 1061–1070. Association for Computational Linguistics, November 2019. https://doi.org/10.18653/v1/D19-1098. https://www.aclweb.org/anthology/D19-1098
Zanzotto, F.M., Dell’Arciprete, L.: Distributed tree kernels. In: Proceedings of the 29th International Conference on Machine Learning, ICML 2012, vol. 1, pp. 193–200 (2012). http://www.scopus.com/inward/record.url?eid=2-s2.0-84867126965&partnerID=MN8TOARS
Zanzotto, F.M., Santilli, A., Ranaldi, L., Onorati, D., Tommasino, P., Fallucchi, F.: KERMIT: complementing transformer architectures with encoders of explicit syntactic interpretations. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 256–267. Association for Computational Linguistics, November 2020. https://doi.org/10.18653/v1/2020.emnlp-main.18. https://www.aclweb.org/anthology/2020.emnlp-main.18
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
Ranaldi, L., Fallucchi, F., Santilli, A., Zanzotto, F.M. (2022). KERMITviz: Visualizing Neural Network Activations on Syntactic Trees. In: Garoufallou, E., Ovalle-Perandones, MA., Vlachidis, A. (eds) Metadata and Semantic Research. MTSR 2021. Communications in Computer and Information Science, vol 1537. Springer, Cham. https://doi.org/10.1007/978-3-030-98876-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-98876-0_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98875-3
Online ISBN: 978-3-030-98876-0
eBook Packages: Computer ScienceComputer Science (R0)