Abstract
With the highly increasing demands, multi-label classification task has attracted more attention in recent years. However, most of traditional methods usually need tedious handcrafted features. Motivated by the remarkably strong performance of deep neural networks on the practically important tasks of natural language processing, we adopted various popular models, such as CNN, RNN and RCNN, to perform multi-label classification tasks for Chinese recipes. Based on the real Chinese recipe data extracted from websites, we compared the performance of deep neural networks in multi-label classification. We also compared them with the baseline models, such as Naive Bayes, MLKNN and fastText. In order to improve the performance of the these models, we adopted the data augmentation method and then conducted extensive experiments to compare different models in our task. The results showed that RCNN model performs the best and can get the highest score. The models based on deep neural networks all performed better than the baseline models. The results also showed that the data augmentation method is a practical method to improve the performance of all models.
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
Cui, X., Goel, V., Kingsbury, B.: Data augmentation for deep neural network acoustic modeling. IEEE/ACM Trans. Audio Speech Lang. Process. 23(9), 1469–1477 (2015)
Dembczynski, K., Cheng, W., Hüllermeier, E.: Bayes optimal multilabel classification via probabilistic classifier chains. In: ICML, pp. 279–286 (2010)
Dembszynski, K., Waegeman, W., Cheng, W., Hüllermeier, E.: On label dependence in multilabel classification. In: Proceedings of the LastCFP: ICML Workshop on Learning from Multi-Label Data, p. 8 (2010)
Ji, S., Tang, L., Yu, S., Ye, J.: A shared-subspace learning framework for multi-label classification. TKDD 4(2), 8:1–8:29 (2010)
Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. CoRR abs/1607.01759 (2016)
Kandola, E.J., Hofmann, T., Poggio, T., Shawe-Taylor, J.: A neural probabilistic language model. Stud. Fuzziness Soft Comput. 194, 137–186 (2006)
Kim, Y.: Convolutional neural networks for sentence classification. CoRR abs/1408.5882 (2014)
Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: INTERSPEECH, pp. 3586–3589 (2015)
Kobayashi, S.: Contextual augmentation: data augmentation by words with paradigmatic relations. CoRR abs/1805.06201 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Lai, S., Xu, L., Liu, K., Zhao, J.: Recurrent convolutional neural networks for text classification. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 2267–2273 (2015)
Liu, P., Qiu, X., Huang, X.: Recurrent neural network for text classification with multi-task learning. CoRR abs/1605.05101 (2016)
Read, J., Pfahringer, B., Holmes, G., Frank, E.: Classifier chains for multi-label classification. Mach. Learn. 85(3), 333–359 (2011). https://doi.org/10.1007/s10994-011-5256-5
Rong, X.: word2vec parameter learning explained. CoRR abs/1411.2738 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 1–9 (2015)
Tsoumakas, G., Katakis, I., Vlahavas, I.P.: Random k-labelsets for multilabel classification. IEEE Trans. Knowl. Data Eng. 23(7), 1079–1089 (2011)
Wei, J.W., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. CoRR abs/1901.11196 (2019)
Wu, X., et al.: Top 10 algorithms in data mining. Knowl. Inf. Syst. 14(1), 1–37 (2008). https://doi.org/10.1007/s10115-007-0114-2
Xia, X., Yang, X., Li, S., Wu, C., Zhou, L.: RW.KNN: a proposed random walk KNN algorithm for multi-label classification. In: Proceedings of the 4th Workshop on Workshop for Ph.D. Students in Information & Knowledge Management, pp. 87–90 (2011)
Zhang, M., Zhou, Z.: ML-KNN: a lazy learning approach to multi-label learning. Pattern Recogn. 40(7), 2038–2048 (2007)
Acknowledgment
This work was supported by the project of Natural Science Foundation of China (No. 61402329, No. 61972456) and the Natural Science Foundation of Tianjin (No. 19JCYBJC15400).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Z., Rong, C., Zhang, X. (2021). Comparisons of Deep Neural Networks in Multi-label Classification for Chinese Recipes. In: Mei, H., et al. Big Data. BigData 2020. Communications in Computer and Information Science, vol 1320. Springer, Singapore. https://doi.org/10.1007/978-981-16-0705-9_12
Download citation
DOI: https://doi.org/10.1007/978-981-16-0705-9_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0704-2
Online ISBN: 978-981-16-0705-9
eBook Packages: Computer ScienceComputer Science (R0)
