Abstract
Reading comprehension is a well studied task, with huge training datasets in English. This work focuses on building reading comprehension systems for Czech, without requiring any manually annotated Czech training data. First of all, we automatically translated SQuAD 1.1 and SQuAD 2.0 datasets to Czech to create training and development data, which we release at http://hdl.handle.net/11234/1-3249. We then trained and evaluated several BERT and XLM-RoBERTa baseline models. However, our main focus lies in cross-lingual transfer models. We report that a XLM-RoBERTa model trained on English data and evaluated on Czech achieves very competitive performance, only approximately 2% points worse than a model trained on the translated Czech data. This result is extremely good, considering the fact that the model has not seen any Czech data during training. The cross-lingual transfer approach is very flexible and provides a reading comprehension in any language, for which we have enough monolingual raw texts.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Available on-line at https://lindat.mff.cuni.cz/services/translation/.
References
Artetxe, M., Labaka, G., Agirre, E.: A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, pp. 789–798. Association for Computational Linguistics, July 2018
Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv e-prints arXiv:1911.02116, November 2019
Conneau, A., Lample, G., Ranzato, M., Denoyer, L., Jégou, H.: Word translation without parallel data. arXiv e-prints arXiv:1710.04087, October 2017
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota, vol. 1, pp. 4171–4186. Association for Computational Linguistics, June 2019
Hsu, T.Y., Liu, C.L., Lee, H.Y.: Zero-shot reading comprehension by cross-lingual transfer learning with multi-lingual language representation model. arXiv e-prints arXiv:1909.09587, September 2019
Kondratyuk, D., Straka, M.: 75 languages, 1 model: parsing universal dependencies universally. 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. 2779–2795. Association for Computational Linguistics, November 2019
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. arXiv e-prints arXiv:1909.11942, September 2019
Lewis, P., Oğuz, B., Rinott, R., Riedel, S., Schwenk, H.: MLQA: evaluating cross-lingual extractive question answering. arXiv e-prints arXiv:1910.07475, October 2019
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv e-prints arXiv:1907.11692, July 2019
Popel, M.: CUNI transformer neural MT system for WMT18. In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, Belgium, Brussels, pp. 482–487. Association for Computational Linguistics, October 2018
Rajpurkar, P., Jia, R., Liang, P.: Know what you don’t know: unanswerable questions for SQuAD. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Melbourne, Australia, pp. 784–789. Association for Computational Linguistics, July 2018
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, pp. 2383–2392. Association for Computational Linguistics, November 2016
Straková, J., Straka, M., Hajič, J.: Open-source tools for morphology, lemmatization, POS tagging and named entity recognition. In: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations. Johns Hopkins University, USA, pp. 13–18. Association for Computational Linguistics, Stroudsburg (2014)
Vidra, J., Žabokrtský, Z., Ševčíková, M., Kyjánek, L.: DeriNet 2.0: towards an all-in-one word-formation resource. In: Proceedings of the Second International Workshop on Resources and Tools for Derivational Morphology, Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics, Prague, Czechia, pp. 81–89, September 2019
Wolf, T., et al.: HuggingFace’s transformers: state-of-the-art natural language processing. arXiv e-prints arXiv:1910.03771, October 2019
Acknowledgements
The work was supported by the Grant Agency of the Czech Republic, project EXPRO LUSyD (GX20-16819X) and by the SVV 260 575 grant of Charles University. This research has also been using data and services provided by the LINDAT/CLARIAH-CZ Research Infrastructure (https://lindat.cz), supported by the Ministry of Education, Youth and Sports of the Czech Republic (Project No. LM2018101).
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
Macková, K., Straka, M. (2020). Reading Comprehension in Czech via Machine Translation and Cross-Lingual Transfer. In: Sojka, P., Kopeček, I., Pala, K., Horák, A. (eds) Text, Speech, and Dialogue. TSD 2020. Lecture Notes in Computer Science(), vol 12284. Springer, Cham. https://doi.org/10.1007/978-3-030-58323-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-58323-1_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58322-4
Online ISBN: 978-3-030-58323-1
eBook Packages: Computer ScienceComputer Science (R0)