Skip to main content
SpringerLink
Log in

Morpheme Based Amharic-Kistanigna Bi-directional Machine Translation Using Deep Learning

  • Conference paper
  • First Online:
Pan-African Conference on Artificial Intelligence (PanAfriCon AI 2022)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1800))

Included in the following conference series:

  • 204 Accesses

Abstract

Machine translation is a natural language processing application that can be used to translate text from one natural language to other natural language. This study attempted to create bidirectional machine translation for Amharic-Kistanigna language. It is critical to develop machine translation between Kistanigna and Amharic languages in order to increase the number of language users, address issues concerning the endangered Kistanigna language, and expand the language’s web contentṄeural Machine Translation is a new approach to machine translation that has achieved a translation quality. The experiments are carried out using LSTM, Bi-LSTM, LSTM + attention, CNN + attention, and Transformer models. We have used 9,225 parallel sentences with morpheme based translation unit. To segment our morpheme data we used the morfessor tool. We considered training time, memory usage, and BLEU score when proposing an optimal model. Finally, we proposed morpheme-based bi-directional machine translation using Transformer with BLEU scores of 21.31 and 22.40 for Amharic-Kistanigna and Kistanigna-Amharic translation respectively. The study’s main weakness is the lack of sufficient datasets to conduct a comprehensive experiment. As a result, parallel corpora are required for conducting similar research.

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 64.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 84.99
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

Similar content being viewed by others

References

  1. Rishita, M.V.S., Raju, M.A., Harris, T.A.: Machine translation using natural language processing. In: MATEC Web Conference, vol. 277, p. 02004 (2019). https://doi.org/10.1051/matecconf/201927702004

  2. B. Abel, “Geez to Amharic Machine Translation,” MSc Thesis, Addis Ababa University, AddisAbaba, Ethiopia (2018)

    Google Scholar 

  3. Okpor, M.D.: Machine translation approaches: issues and challenges. Int. J. Comput. Sci. Issues, 11(5), 159–165 (2014). https://www.IJCSI.org

  4. Tripathi, S., Sarkhel, J.: Approaches to machine translation. Ann. Libr. Inf. Stud. 57(4), 388–393 (2010)

    Google Scholar 

  5. Genet, W.: “Ge ez-amharic machine translation using deep learning,” MSc Thesis, Bahir Dar University, Bahir Dar, Ethiopia (2021)

    Google Scholar 

  6. Daba, J., Assabie, Y.: A hybrid approach to the development of bidirectional English-Oromiffa machine translation. In: Przepiórkowski, A., Ogrodniczuk, M. (eds.) NLP 2014. LNCS (LNAI), vol. 8686, pp. 228–235. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10888-9_24

    Chapter  Google Scholar 

  7. Abate, S.T., et al.: “Parallel Corpora for bi Directional Statistical Machine Translation for Seven Ethiopian Language Pairs,” October, vol. 1, pp. 153–156 (2018)

    Google Scholar 

  8. Gurmu, A.Y., et al.: The, “Word formation in K + stantfifia," MSc Thesis, Addis Ababa University, Addis Ababa, Ethiopia. No. January (2000)

    Google Scholar 

  9. Deriba, F.G.: “Developing part of speech tagger for guragigna language”, MSc Thesis, Bahir Dar University, Bahir Dar, Ethiopia (2017)

    Google Scholar 

  10. Tadesse, K.: “Morpheme-Based Bi directional Ge’ez-Amharic Machine Translation”, MSc Thesis, Addis Ababa University, Addis Ababa, Ethiopia (2018)

    Google Scholar 

  11. Chen, M., Li, Y., Li, R.: Research on neural machine translation model. In: Journal of Physics: Conference Series, vol. 1237, no. 5 (2019). https://doi.org/10.1088/1742-6596/1237/5/052020

  12. Nouhaila, B., Habib, A., Abdellah, A., Abdelhamid, I. E. F.: Arabic machine translation using Bidirectional LSTM Encoder-Decoder (2017). https://indabaxmorocco.github.io/materials/posters/Bensalah.pdf

  13. Arfaso, B.: “Bi-Directional English-Afan Oromo Machine Translation Using Convolutional Neural Network,” MSc Thesis, Addis Ababa University, Addis Ababa, Ethiopia (2019)

    Google Scholar 

  14. Workinhe, W.: “Attention-based Amharic-to Wolaita Neural Machine Translation”, MSc Thesis, Addis Ababa University, Addis Ababa, Ethiopia (2020)

    Google Scholar 

  15. Mindaye, T.: “Design and Implementation of Amharic search engine,” MSc Thesis, Addis Ababa University, Addis Ababa, Ethiopia (2007)

    Google Scholar 

  16. Adamkew, K.: “Ge ez-Amharic machine translation using RNN,” MSc Thesis, Bahir Dar University, Bahir Dar, Ethiopia (2021)

    Google Scholar 

  17. Negia, M.K., Tamiru, R.M., Meshesha, M.: “Amharic-Kistanigna bi-directional machine translation using deep learning. In: 2022 International Conference on Information and Communication Technology for Development for Africa (ICT4DA), Bahir Dar, Ethiopia, pp. 61–65 (2022). https://doi.org/10.1109/ICT4DA56482.2022.9971194

Download references

Author information

Authors and Affiliations

  1. Bahir Dar Institute of Technology, Bahir Dar University, Bahir Dar, Ethiopia

    Mengistu Kinfe Negia & Rahel Mekonen Tamiru

  2. Addis Ababa University, Addis Ababa, Ethiopia

    Million Meshesha

Authors
  1. Mengistu Kinfe Negia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rahel Mekonen Tamiru
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Million Meshesha
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mengistu Kinfe Negia .

Editor information

Editors and Affiliations

  1. Ethiopian Artificial Intelligence Institute, Addis Ababa, Ethiopia

    Taye Girma Debelee

  2. HAWK University of Applied Sciences and Arts, Göttingen, Germany

    Achim Ibenthal

  3. University of Ulm, Ulm, Germany

    Friedhelm Schwenker

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Negia, M.K., Tamiru, R.M., Meshesha, M. (2023). Morpheme Based Amharic-Kistanigna Bi-directional Machine Translation Using Deep Learning. In: Girma Debelee, T., Ibenthal, A., Schwenker, F. (eds) Pan-African Conference on Artificial Intelligence. PanAfriCon AI 2022. Communications in Computer and Information Science, vol 1800. Springer, Cham. https://doi.org/10.1007/978-3-031-31327-1_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-31327-1_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-31326-4

  • Online ISBN: 978-3-031-31327-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation