Abstract
Most dense word embedding methods are based on statistics and semantic information currently. However, for hieroglyphs, these methods ignore the visual information underlaid in the characters, moreover this visual information in the expression of characters plays an extremely important role. Therefore, the visual information can be uncovered from the single character image through Convolutional Neural Network (CNN). Compared with the mainstream methods, the CNN method is inferior in efficiency and precision. In this study, we present a novel model called Img2Vec: using Principal Component Analysis (PCA) to generate word embedding vectors. Because the semantic and the visual information of the characters are complementary, we feed Word2Vec and Img2Vec embeddings into two different fusion models to implement text classification. Experiments show that our Img2Vec model has significant improvements in training time and precision. Finally, the visualizations of our Img2Vec character embedding prove that our model has a state-of-the-art representation of the visual information.
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
References
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3(10), 993–1022 (2003)
Dhingra, B., Zhou, Z., Fitzpatrick, D., Muehl, M., Cohen, W.W.: Tweet2vec: character-based distributed representations for social media, pp. 269–274, May 2016
Gillick, D., Brunk, C., Vinyals, O., Subramanya, A.: Multilingual language processing from bytes, November 2015
Harris, Z.S.: Distributional structure. In: Hiż, H. (ed.) Papers on Syntax. SLAP, vol. 14, pp. 3–22. Springer, Dordrecht (1981). https://doi.org/10.1007/978-94-009-8467-7_1
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Hunter, J.D.: Matplotlib: a 2D graphics environment. Comput. Sci. Eng. 9(3), 90–95 (2007)
Iyyer, M., Manjunatha, V., Boyd-Graber, J., Daumé III, H.: Deep unordered composition rivals syntactic methods for text classification. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, (Volume 1: Long Paper), vol. 1, pp. 1681–1691 (2015)
Jones, R., Rey, B., Madani, O., Greiner, W.: Generating query substitutions. In: Proceedings of the 15th International Conference on World Wide Web, pp. 387–396. ACM (2006)
Jozefowicz, R., Vinyals, O., Schuster, M., Shazeer, N., Wu, Y.: Exploring the limits of language modeling, February 2016
Kingma, D., Ba, J.: Adam: a method for stochastic optimization, December 2014
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: Proceedings of the 31st International Conference on Machine Learning (ICML 2014), pp. 1188–1196 (2014)
Liou, C.Y., Cheng, W.C., Liou, J.W., Liou, D.R.: Autoencoder for words. Neurocomputing 139, 84–96 (2014)
Liou, C.Y., Huang, J.C., Yang, W.C.: Modeling word perception using the elman network. Neurocomputing 71(16), 3150–3157 (2008)
Liu, F., Lu, H., Lo, C., Neubig, G.: Learning character-level compositionality with visual features. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2059–2068. Association for Computational Linguistics, Vancouver, July 2017. http://aclweb.org/anthology/P17-1188
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space, January 2013
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Paşca, M., Lin, D., Bigham, J., Lifchits, A., Jain, A.: Names and similarities on the web: fact extraction in the fast lane. In: Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics, pp. 809–816. Association for Computational Linguistics (2006)
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)
Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)
Taft, M., Zhu, X., Peng, D.: Positional specificity of radicals in Chinese character recognition. J. Memory Lang. 40(4), 498–519 (1999)
Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156–3164 (2015)
Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems, pp. 649–657 (2015)
Acknowledgments
This paper was supported by the National Science Foundation of China (Grant No. 61702350).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
He, L. et al. (2018). Visual-Based Character Embedding via Principal Component Analysis. In: Zhou, Q., Gan, Y., Jing, W., Song, X., Wang, Y., Lu, Z. (eds) Data Science. ICPCSEE 2018. Communications in Computer and Information Science, vol 901. Springer, Singapore. https://doi.org/10.1007/978-981-13-2203-7_16
Download citation
DOI: https://doi.org/10.1007/978-981-13-2203-7_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2202-0
Online ISBN: 978-981-13-2203-7
eBook Packages: Computer ScienceComputer Science (R0)