Abstract
State-of-the-art machine translation (MT) systems rely on the availability of large parallel corpora, containing millions of sentence pairs. For the Icelandic language, the parallel corpus ParIce exists, consisting of about 3.6 million English-Icelandic sentence pairs. Given that parallel corpora for low-resource languages typically contain sentence pairs in the tens or hundreds of thousands, we classify Icelandic as a medium-resource language for MT purposes. In this paper, we present on-going experiments with different MT models, both statistical and neural, for translating English to Icelandic based on ParIce. We describe the corpus and the filtering process used for removing noisy segments, the different models used for training, and the preliminary automatic and human evaluation. We find that, while using an aggressive filtering approach, the most recent neural MT system (Transformer) performs best, obtaining the highest BLEU score and the highest fluency and adequacy scores from human evaluation for in-domain translation. Our work could be beneficial to other languages for which a similar amount of parallel data is available.
H. P. Jónsson, H. B. Símonarson, V. Snæbjarnarson, S. Steingrímsson—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Bengio, Y., LeCun, Y. (eds.) Proceedings of the 3rd International Conference on Learning Representations, ICLR, San Diego (2015)
Barkarson, S., Steingrímsson, S.: Compiling and filtering ParIce: an English-icelandic parallel corpus. In: Proceedings of the 22nd Nordic Conference on Computational Linguistics, NODALIDA, Turku, Finland (2019)
Bentivogli, L., Bisazza, A., Cettolo, M., Federico, M.: Neural versus phrase-based machine translation quality: a case study. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP, Austin, TX, USA (2016)
Brandt, M.D., Loftsson, H., Sigurþórsson, H., Tyers, F.M.: Apertium-IceNLP: a rule-based Icelandic to English machine translation system. In: Proceedings of the 15th Annual Conference of the European Association for Machine Translation, EAMT, Leuven, Belgium (2011)
Castilho, S., Moorkens, J., Gaspari, F., Calixto, I., Tinsley, J., Way, A.: Is neural machine translation the new state of the art? Prague Bull. Math. Linguist. 108(1), 109–120 (2017)
Defauw, A., Vanallemeersch, T., Van Winckel, K., Szoc, S., Van den Bogaert, J.: Being generous with sub-words towards small NMT children. In: Proceedings of the 12th Language Resources and Evaluation Conference, LREC, Marseille, France (2020)
Heafield, K., Pouzyrevsky, I., Clark, J.H., Koehn, P.: Scalable modified Kneser-Ney language model estimation. In: Proceeedings of 51st Annual Meeting of the Association for Computational Linguistics, ACL, Sofia, Bulgaria (2013)
Jassem, K., Dwojak, T.: Statistical versus neural machine translation - a case study for a medium size domain-specific bilingual corpus. Poznan Stud. Contemp. Linguist. 55(2), 491–515 (2019)
Johnson, M., Firat, O., Aharoni, R.: Massively multilingual neural machine translation. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), NAACL, Minneapolis, MN, USA (2019)
Koehn, P.: Statistical Machine Translation. Cambridge University Press, Cambridge (2009)
Koehn, P., Knowles, R.: Six challenges for neural machine translation. In: Proceedings of the First Workshop on Neural Machine Translation, Vancouver, Canada (2017)
Koo, T., Li, M.: A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J. Chiropractic Med. 15, 155–163 (2016)
Kudo, T., Richardson, J.: SentencePiece: a simple and language independent subword tokenizer and detokenizer for Neural Text Processing. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP, Brussels, Belgium (2018)
Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP, Lisbon, Portugal (2015)
Pinnis, M.: Tilde’s parallel corpus filtering methods for WMT 2018. In: Proceedings of the Third Conference on Machine Translation: Shared Task Papers, Brussels, Belgium (2018)
Reiter, E.: A structured review of the validity of BLEU. Comput. Linguist. 44(3), 393–401 (2018)
Rozis, R., Skadiņš, R.: Tilde MODEL - multilingual open data for EU languages. In: Proceedings of the 21st Nordic Conference on Computational Linguistics, NODALIDA, Gothenburg, Sweden (2017)
Steingrímsson, S., Helgadóttir, S., Rögnvaldsson, E., Barkarson, S., Gunason, J.: Risamálheild: a very large icelandic text corpus. In: Proceedings of the 11th International Conference on Language Resources and Evaluation, LREC, Miyazaki, Japan, May 2018
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, NIPS, Montreal, Canada (2014)
Tiedemann, J.: Parallel data, tools and interfaces in OPUS. In: Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012, Istanbul, Turkey (2012)
Varga, D., Németh, L., Halácsy, P., Kornai, A., Viktor Trón, V.N.: Parallel corpora for medium density languages. In: Proceedings of Recent Advances in Natural Language Processing, RANLP, Borovets, Bulgaria (2005)
Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 5998–6008. Curran Associates, Inc. (2017)
Acknowledgments
This project was funded by the Language Technology Programme for Icelandic 2019–2023. The programme, which is managed and coordinated by Almannarómur, is funded by the Icelandic Ministry of Education, Science and Culture.
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
Jónsson, H.P., Símonarson, H.B., Snæbjarnarson, V., Steingrímsson, S., Loftsson, H. (2020). Experimenting with Different Machine Translation Models in Medium-Resource Settings. 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_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-58323-1_10
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)