Abstract
Data Augmentation methods – a family of techniques designed for synthetic generation of training data – have shown remarkable results in various Deep Learning and Machine Learning tasks. Despite its widespread and successful adoption within the computer vision community, data augmentation techniques designed for natural language processing (NLP) tasks have exhibited much slower advances and limited success in achieving performance gains. As a consequence, with the exception of applications of back-translation to machine translation tasks, these techniques have not been as thoroughly explored by the wider NLP community. Recent research on the subject also still lacks a proper practical understanding of the relationship between data augmentation and several important aspects of model design, such as hyperparameters and regularization parameters. In this paper, we perform a comprehensive study of NLP data augmentation techniques, comparing their relative performance under different settings. We also propose Deep Back-Translation, a novel NLP data augmentation technique and apply it to benchmark datasets. We analyze the quality of the synthetic data generated, evaluate its performance gains and compare all of these aspects to previous existing data augmentation procedures.
Partially supported by Itaú-Unibanco, CNPq (grants 25860/2016-7 and 530307027/2017-1), and CAPES (Finance Code 001). Any opinions, findings, and conclusions expressed in this manuscript are those of the authors and do not necessarily reflect the views, official policy or position of Itaú-Unibanco.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
References
Bao, F., Neumann, M., Vu, T.: CycleGAN-based emotion style transfer as data augmentation for speech emotion recognition. In: Proceedings of the Interspeech 2019, pp. 2828–2832, September 2019. https://doi.org/10.21437/Interspeech.2019-2293
Basile, V., et al.: SemEval-2019 task 5: multilingual detection of hate speech against immigrants and women in twitter. In: Proceedings of the 13th International Workshop on Semantic Evaluation, pp. 54–63. Association for Computational Linguistics, Minneapolis, June 2019. https://doi.org/10.18653/v1/S19-2007
Caswell, I., Chelba, C., Grangier, D.: Tagged back-translation. In: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), pp. 53–63. Association for Computational Linguistics, Florence, August 2019. https://doi.org/10.18653/v1/W19-5206
Cortis, K., et al.: SemEval-2017 task 5: fine-grained sentiment analysis on financial microblogs and news. In: Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pp. 519–535. Association for Computational Linguistics, Stroudsburg (2017). https://doi.org/10.18653/v1/S17-2089
Dao, T., Gu, A., Ratner, A., Smith, V., De Sa, C., Re, C.: A kernel theory of modern data augmentation. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 1528–1537. PMLR, Long Beach, 09–15 June 2019. http://proceedings.mlr.press/v97/dao19b.html
Davis, B., Cortis, K., Vasiliu, L., Koumpis, A., Mcdermott, R., Handschuh, S.: Social sentiment indices powered by X-scores. In: ALLDATA 2016, The Second International Conference on Big Data, Small Data, Linked Data and Open Data, Lisbon, Portugal (2016)
Edunov, S., Ott, M., Auli, M., Grangier, D.: Understanding back-translation at scale. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 489–500. Association for Computational Linguistics, Brussels, October–November 2018. https://doi.org/10.18653/v1/D18-1045
Ferreira, T., Paiva, F., Silva, R., Paula, A., Costa, A., Cugnasca, C.: Assessing regression-based sentiment analysis techniques in financial texts. In: Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional, pp. 729–740. SBC, Porto Alegre (2019). https://doi.org/10.5753/eniac.2019.9329, https://sol.sbc.org.br/index.php/eniac/article/view/9329
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. The MIT Press, Cambridge (2016)
Graça, M., Kim, Y., Schamper, J., Khadivi, S., Ney, H.: Generalizing back-translation in neural machine translation. In: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), pp. 45–52. Association for Computational Linguistics, Florence, August 2019. https://doi.org/10.18653/v1/W19-5205
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
Hernández-García, A., König, P.: Further advantages of data augmentation on convolutional neural networks. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 95–103. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01418-6_10
Hoang, V.C.D., Koehn, P., Haffari, G., Cohn, T.: Iterative back-translation for neural machine translation. In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 18–24. Association for Computational Linguistics, Melbourne, July 2018. https://doi.org/10.18653/v1/W18-2703
Imamura, K., Fujita, A., Sumita, E.: Enhancement of encoder and attention using target monolingual corpora in neural machine translation. In: Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pp. 55–63. Association for Computational Linguistics, Melbourne, July 2018. https://doi.org/10.18653/v1/W18-2707
Kobayashi, S.: Contextual augmentation: data augmentation by words with paradigmatic relations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 452–457. Association for Computational Linguistics, New Orleans, June 2018. https://doi.org/10.18653/v1/N18-2072
Konda, K.R., Bouthillier, X., Memisevic, R., Vincent, P.: Dropout as data augmentation. arXiv abs/1506.08700 (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems. NIPS 2012, vol. 1, pp. 1097–1105. Curran Associates Inc., Red Hook (2012)
Mikołajczyk, A., Grochowski, M.: Data augmentation for improving deep learning in image classification problem. In: 2018 International Interdisciplinary PhD Workshop (IIPhDW), pp. 117–122 (2018)
Mohammad, S., Bravo-Marquez, F., Salameh, M., Kiritchenko, S.: SemEval-2018 task 1: affect in tweets. In: Proceedings of The 12th International Workshop on Semantic Evaluation, pp. 1–17. Association for Computational Linguistics, New Orleans, June 2018. https://doi.org/10.18653/v1/S18-1001
Pennington, J., Socher, R., Manning, C.D.: GloVe : global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Salamon, J., Bello, J.P.: Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24(3), 279–283 (2017)
Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 86–96. Association for Computational Linguistics, Berlin, August 2016. https://doi.org/10.18653/v1/P16-1009
Springenberg, J., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: The all convolutional net. In: ICLR (workshop track) (2015). http://lmb.informatik.uni-freiburg.de/Publications/2015/DB15a
Sugiyama, A., Yoshinaga, N.: Data augmentation using back-translation for context-aware neural machine translation. In: Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), pp. 35–44. Association for Computational Linguistics, Hong Kong, November 2019. https://doi.org/10.18653/v1/D19-6504
Taylor, L., Nitschke, G.: Improving deep learning with generic data augmentation. In: 2018 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1542–1547 (2018)
Wei, J., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks. 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), pp. 6382–6388. Association for Computational Linguistics, Hong Kong, November 2019. https://doi.org/10.18653/v1/D19-1670
Wen, Q., Sun, L., Song, X., Gao, J., Wang, X., Xu, H.: Time series data augmentation for deep learning: a survey (2020)
Yu, A.W., et al.: QANET: combining local convolution with global self-attention for reading comprehension. CoRR abs/1804.09541 (2018). https://arxiv.org/pdf/1804.09541
Zhang, Y., Wallace, B.C.: A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification. In: Proceedings of the 8th International Joint Conference on Natural Language Processing, pp. 253–263 (2017)
Zhao, D., Yu, G., Xu, P., Luo, M.: Equivalence between dropout and data augmentation: a mathematical check. Neural Netw. Off. J. Int. Neural Netw. Soc. 115, 82–89 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Maier Ferreira, T., Reali Costa, A.H. (2020). DeepBT and NLP Data Augmentation Techniques: A New Proposal and a Comprehensive Study. In: Cerri, R., Prati, R.C. (eds) Intelligent Systems. BRACIS 2020. Lecture Notes in Computer Science(), vol 12319. Springer, Cham. https://doi.org/10.1007/978-3-030-61377-8_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-61377-8_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61376-1
Online ISBN: 978-3-030-61377-8
eBook Packages: Computer ScienceComputer Science (R0)