Skip to main content
SpringerLink
Log in

Experimenting with Different Machine Translation Models in Medium-Resource Settings

  • Conference paper
  • First Online:
Text, Speech, and Dialogue (TSD 2020)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 12284))

Included in the following conference series:

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.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    http://www.statmt.org/moses/.

  2. 2.

    https://opennmt.net/.

  3. 3.

    https://github.com/tensorflow/tensor2tensor.

  4. 4.

    https://github.com/paracrawl/keops.

References

  1. 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)

    Google Scholar 

  2. 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)

    Google Scholar 

  3. 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)

    Google Scholar 

  4. 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)

    Google Scholar 

  5. 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)

    Article  Google Scholar 

  6. 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)

    Google Scholar 

  7. 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)

    Google Scholar 

  8. 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)

    Article  Google Scholar 

  9. 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)

    Google Scholar 

  10. Koehn, P.: Statistical Machine Translation. Cambridge University Press, Cambridge (2009)

    Book  Google Scholar 

  11. Koehn, P., Knowles, R.: Six challenges for neural machine translation. In: Proceedings of the First Workshop on Neural Machine Translation, Vancouver, Canada (2017)

    Google Scholar 

  12. Koo, T., Li, M.: A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J. Chiropractic Med. 15, 155–163 (2016)

    Article  Google Scholar 

  13. 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)

    Google Scholar 

  14. 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)

    Google Scholar 

  15. 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)

    Google Scholar 

  16. Reiter, E.: A structured review of the validity of BLEU. Comput. Linguist. 44(3), 393–401 (2018)

    Article  Google Scholar 

  17. 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)

    Google Scholar 

  18. 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

    Google Scholar 

  19. 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)

    Google Scholar 

  20. 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)

    Google Scholar 

  21. 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)

    Google Scholar 

  22. 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)

    Google Scholar 

Download references

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

  1. Language and Voice Lab, Reykjavik University, Reykjavik, Iceland

    Haukur Páll Jónsson, Steinþór Steingrímsson & Hrafn Loftsson

  2. Mieind ehf., Reykjavik, Iceland

    Haukur Barri Símonarson & Vésteinn Snæbjarnarson

Authors
  1. Haukur Páll Jónsson
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Haukur Barri Símonarson
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Vésteinn Snæbjarnarson
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Steinþór Steingrímsson
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hrafn Loftsson
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hrafn Loftsson .

Editor information

Editors and Affiliations

  1. Faculty of Informatics, Masaryk University, Brno, Czech Republic

    Petr Sojka

  2. Faculty of Informatics, Masaryk University, Brno, Czech Republic

    Ivan Kopeček

  3. Faculty of Informatics, Masaryk University, Brno, Czech Republic

    Karel Pala

  4. Faculty of Informatics, Masaryk University, Brno, Czech Republic

    Aleš Horák

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

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)

Publish with us

Policies and ethics

Search

Navigation