[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/langstream-2026-sliwa-machine-translation-between-english-syriac/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [Aramaic](https://md.mova.elamur.ai/free/en/docs/papers/arc/) / Machine Translation between English and Syriac (East Syriac Dialect) using Statistical Machine Learning

# Machine Translation between English and Syriac (East Syriac Dialect) using Statistical Machine Learning

**Authors:** Hadiana Sliwa; [Hossein Hassani](https://md.mova.elamur.ai/free/en/docs/papers/authors/hossein-hassani/) · **Year:** 2026 · **Venue:** arXiv:2609.18529 **Link:** [arxiv.org/abs/2609.18529](https://arxiv.org/abs/2609.18529) · library `langstream-2026-sliwa-machine-translation-between-english-syriac` · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) (arXiv)

[**0** citations](https://openalex.org/works?filter=cites:W7213510361) openalex-snapshot · 2026-10-14[arXiv:2609.18529](https://openalex.org/S4306400194)[licence](http://creativecommons.org/licenses/by/4.0/)

- [Publisher's page](https://arxiv.org/abs/2609.18529)
- [PDF](https://arxiv.org/pdf/2609.18529)
- [arXiv 2609.18529](https://arxiv.org/abs/2609.18529)
- [OpenAlex](https://openalex.org/W7213510361)

**Authors (2)**

1. [Hadiana Sliwa](https://openalex.org/A5152036207) h 0 · 0 citations · 1 works
2. [Hossein Hassani](https://openalex.org/A5098752785) [ORCID](https://orcid.org/0000-0003-1896-2075) · h 3 · 17 citations · 9 works

Citations and author metrics from openalex-snapshot (2026-10-14); authors with the same name are not always told apart.

## What it is about

The authors build a first phrase-based statistical MT system between English and East Syriac, using Moses with GIZA++ alignment, KenLM language models and MERT tuning. The corpus has 38,847 verse-aligned sentence pairs from the Bible: the New Testament from existing data, and the Old Testament extracted from PDFs and checked by hand. Before training, the Syriac side is devocalised (vowel marks removed) and split with byte-pair encoding. Across four splits (95/5 to 70/30), word-level BLEU falls from 22.54 to 17.81. The best model, with an operation sequence model and a 5-gram language model, reaches 23.54. Eleven native speakers rated 20 sentences, giving a mean adequacy of 3.42 and fluency of 3.34 out of 5, with a correlation of 0.865 between the two.

## Ideas

- I1. Devocalisation as a measured step: parse the same verses pointed and unpointed, and report the drop in UAS and LAS on `treebanks/hbo/ptnk`. This is the test that shows how much the unpointed mode of `tools/hbo` loses, and it is a number, not an assumption.
- I2. Verse numbers as anchors for parallel Aramaic and Hebrew texts: split by chapter and verse, pair the segments, then check a random sample by hand, as the paper does for the Bible. Use this to build the parallel side for the Targum and Peshitta notes in [Biblical Aramaic texts, annotated](https://md.mova.elamur.ai/free/en/docs/languages/arc/texts/).
- I3. Report the training-size curve and a small human panel together, with adequacy and fluency separated and their correlation given. For an Aramaic test set, record the curve and a 20-sentence human check, not BLEU alone.

## For Mova

I1 goes into `tools/hbo` (pointed versus unpointed) on `treebanks/hbo/ptnk`. I2 goes into [Biblical Aramaic texts, annotated](https://md.mova.elamur.ai/free/en/docs/languages/arc/texts/). I3 is an evaluation habit for the Aramaic tests. The paper is an SMT baseline, and Mova's own translation is not SMT, so no translation method is taken from it.

Topics: [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/)

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [arXiv 2609.18529](https://arxiv.org/abs/2609.18529)

```
@misc{sliwa2026machine,
  title = {{Machine Translation between English and Syriac (East Syriac Dialect) using Statistical Machine Learning}},
  author = {Sliwa, Hadiana and Hassani, Hossein},
  year = {2026},
  eprint = {2609.18529},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.18529}
}
```

- [← previous NoLoR: An ASR-Based Framework for Expedited Endangered Language Documentation with Neo-Aramaic as a Case Study](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2024-nazari-nolor-asr-based-framework-expedited/)
- [next → CCASH: A Web Application Framework for Efficient, Distributed Language Resource Development](https://md.mova.elamur.ai/free/en/docs/papers/lingbulk-2010-felt-ccash-web-application-framework-efficient/)
- [↑ back to Aramaic](https://md.mova.elamur.ai/free/en/docs/papers/arc/)

## References

28 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ahmadi, S., Hassani, H., and Jaff, D. Q. (2022). Leveraging Multilingual News Websites for Building a Kurdish Parallel Corpus. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 21(5), April. [↗](https://doi.org/10.1145/3511806)
2. Al-Onaizan, Y., Curin, J., Jahr, M., Knight, K., Lafferty, J., Melamed, D., Och, F.-J., Purdy, D., Smith, N. A., and Yarowsky, D. (1999). Statistical Machine Translation: Final Report, JHU Workshop 1999. Final report, Center for Speech and Language Processing, Johns Hopkins University. [find](https://scholar.google.com/scholar?q=Al%2DOnaizan%2C+Y%2E%2C+Curin%2C+J%2E%2C+Jahr%2C+M%2E%2C+Knight%2C+K%2E%2C+Lafferty%2C+J%2E%2C+Melamed%2C+D%2E%2C+Och%2C+F%2E%2DJ%2E%2C+Purdy%2C+D%2E%2C+Smith%2C+N%2E+A%2E%2C+and+Yarowsky%2C+D%2E+%281999%29%2E+Statistical+Machine+Translation%3A+Final+Report%2C+JHU+Workshop+19)
3. Armya, R. E. and Abdulrazzaq, M. B. (2024). Handwritten Character Recognition in Assyrian Language Using Convolutional Neural Network. Science Journal of University of Zakho, 12(1):105–115, Mar. [↗](https://doi.org/10.25271/sjuoz.2024.12.1.1189)
4. Artstein, R. and Poesio, M. (2008). Survey Article: Inter-Coder Agreement for Computational Linguistics. Computational Linguistics, 34(4):555–596. [↗](https://doi.org/10.1162/coli.07-034-r2)
5. Boujkian, S. (2025). Improving Low-Resource Machine Translation via Cross-Linguistic Transfer from Typologically Similar High-Resource Languages. [↗](https://doi.org/10.48550/arxiv.2501.00045)
6. Brock, S. (2017). An Introduction to Syriac Studies. Gorgias Handbooks. Gorgias Press LLC, Piscataway, NJ, 3rd edition. [↗](https://doi.org/10.31826/9781463237820)
7. Carpuat, M., Marton, Y., and Habash, N. (2010). Improving Arabic-to-English Statistical Machine Translation by Reordering Post-verbal Subjects for Alignment. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL 2010), pages 178–183. [find](https://scholar.google.com/scholar?q=Carpuat%2C+M%2E%2C+Marton%2C+Y%2E%2C+and+Habash%2C+N%2E+%282010%29%2E+Improving+Arabic%2Dto%2DEnglish+Statistical+Machine+Translation+by+Reordering+Post%2Dverbal+Subjects+for+Alignment%2E+In+Proceedings+of+the+Human+Language+Techn)
8. Durrani, N., Schmid, H., and Fraser, A. (2011). A Joint Sequence Translation Model with Integrated Reordering. In Dekang Lin, et al., editors, Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 1045–1054, Portland, Oregon, USA, June. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Durrani%2C+N%2E%2C+Schmid%2C+H%2E%2C+and+Fraser%2C+A%2E+%282011%29%2E+A+Joint+Sequence+Translation+Model+with+Integrated+Reordering%2E+In+Dekang+Lin%2C+et+al%2E%2C+editors%2C+Proceedings+of+the+49th+Annual+Meeting+of+the+Association)
9. Fernández, A. and Matamala, A. (2021). Human Evaluation of Three Machine Translation Systems: From Quality to Attitudes by Professional Translators. Vigo International Journal of Applied Linguistics, pages 123–148, 01. [find](https://scholar.google.com/scholar?q=Fern%C3%A1ndez%2C+A%2E+and+Matamala%2C+A%2E+%282021%29%2E+Human+Evaluation+of+Three+Machine+Translation+Systems%3A+From+Quality+to+Attitudes+by+Professional+Translators%2E+Vigo+International+Journal+of+Applied+Linguistics%2C+)
10. Guellil, I., Azouaou, F., and Abbas, M. (2007). Neural Vs Statistical Translation of Algerian Arabic Dialect written with Arabizi and Arabic letter. In Neural Vs Statistical Translation of Algerian Arabic Dialect written with Arabizi and Arabic letter, 11. [find](https://scholar.google.com/scholar?q=Guellil%2C+I%2E%2C+Azouaou%2C+F%2E%2C+and+Abbas%2C+M%2E+%282007%29%2E+Neural+Vs+Statistical+Translation+of+Algerian+Arabic+Dialect+written+with+Arabizi+and+Arabic+letter%2E+In+Neural+Vs+Statistical+Translation+of+Algerian+Ar)
11. Habash, N. and Sadat, F. (2006). Arabic Preprocessing Schemes for Statistical Machine Translation. In Proceedings of the Human Language Technology Conference of the North American Chapter of the ACL (HLT-NAACL), pages 49–52. [↗](https://doi.org/10.3115/1614049.1614062)
12. Hassan, H., Aue, A., Chen, C., Chowdhary, V., Clark, J., Federmann, C., Huang, X., Junczys-Dowmunt, M., Lewis, W., Li, M., Liu, S., Liu, T.-Y., Luo, R., Menezes, A., Qin, T., Seide, F., Tan, X., Tian, F., Wu, L., Wu, S., Xia, Y., Zhang, D., Zhang, Z., and Zhou, M. (2018). Achieving Human Parity on Automatic Chinese to English News Translation. [↗](https://doi.org/10.48550/arxiv.1803.05567)
13. Kakum, N. and Sambyo, K. (2022). Phrase-Based English–Nyishi Machine Translation, 09. [find](https://scholar.google.com/scholar?q=Kakum%2C+N%2E+and+Sambyo%2C+K%2E+%282022%29%2E+Phrase%2DBased+English%E2%80%93Nyishi+Machine+Translation%2C+09%2E)
14. Kiraz, G. A. (2011). Forty years of syriac computing. Hugoye: Journal of Syriac Studies, 10(1):33–54. [↗](https://doi.org/10.31826/hug-2011-100106)
15. Kiraz, G. (2013). The New Syriac Primer: An Introduction to the Syriac Language. Gorgias Handbooks. Gorgias Press, Piscataway, NJ. [find](https://scholar.google.com/scholar?q=Kiraz%2C+G%2E+%282013%29%2E+The+New+Syriac+Primer%3A+An+Introduction+to+the+Syriac+Language%2E+Gorgias+Handbooks%2E+Gorgias+Press%2C+Piscataway%2C+NJ%2E)
16. Koehn, P. and Knowles, R. (2017). Six Challenges for Neural Machine Translation. In Thang Luong, et al., editors, Proceedings of the First Workshop on Neural Machine Translation, pages 28–39, Vancouver, August. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/w17-3204)
17. Koehn, P., Och, F. J., and Marcu, D. (2003). Statistical Phrase-based Translation. In Proceedings of NAACL-HLT, pages 48–54. [↗](https://doi.org/10.21236/ada461156)
18. Kumar, S., Anastasopoulos, A., Wintner, S., and Tsvetkov, Y. (2021). Machine Translation into Low-resource Language Varieties. In Chengqing Zong, et al., editors, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 110–121, Online, August. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2021.acl-short.16)
19. Liebeskind, C., Liebeskind, S., and Bouhnik, D. (2024). Machine Translation for Historical Research: A Case Study of Aramaic-Ancient Hebrew Translations. J. Comput. Cult. Herit., 17(2), February. [↗](https://doi.org/10.1145/3627168)
20. Majeed, A. and Hassani, H. (2024). Ancient but Digitized: Developing Handwritten Optical Character Recognition for East Syriac Script Through Creating KHAMIS Dataset. Department of Computer Science. [↗](https://doi.org/10.48550/arxiv.2408.13631) [our card](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2024-majeed-ancient-but-digitized-developing-handwritten/)
21. Muraoka, T. (2005). Classical Syriac: A Basic Grammar with a Chrestomathy, volume 19 of Porta Linguarum Orientalium, Neue Serie. Harrassowitz Verlag, Wiesbaden, 2nd, revised edition. [find](https://scholar.google.com/scholar?q=Muraoka%2C+T%2E+%282005%29%2E+Classical+Syriac%3A+A+Basic+Grammar+with+a+Chrestomathy%2C+volume+19+of+Porta+Linguarum+Orientalium%2C+Neue+Serie%2E+Harrassowitz+Verlag%2C+Wiesbaden%2C+2nd%2C+revised+edition%2E)
22. Naaijer, M., Sikkel, C., Coeckelbergs, M., Attema, J., and Van Peursen, W. T. (2023). A Transformer-based parser for Syriac morphology. In Adam Anderson, et al., editors, Proceedings of the Ancient Language Processing Workshop, pages 23–29, Varna, Bulgaria, September. INCOMA Ltd., Shoumen, Bulgaria. [find](https://scholar.google.com/scholar?q=Naaijer%2C+M%2E%2C+Sikkel%2C+C%2E%2C+Coeckelbergs%2C+M%2E%2C+Attema%2C+J%2E%2C+and+Van+Peursen%2C+W%2E+T%2E+%282023%29%2E+A+Transformer%2Dbased+parser+for+Syriac+morphology%2E+In+Adam+Anderson%2C+et+al%2E%2C+editors%2C+Proceedings+of+the+Ancient+La) [our card](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2023-naaijer-transformer-based-parser-syriac-morphology/)
23. Papineni, K., Roukos, S., Ward, T., and Zhu, W.-J. (2002). Bleu: a Method for Automatic Evaluation of Machine Translation. In Pierre Isabelle, et al., editors, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA, July. Association for Computational Linguistics. [↗](https://doi.org/10.3115/1073083.1073135) [our card](https://md.mova.elamur.ai/free/en/docs/papers/papineni-2002-bleu-method-automatic-evaluation-machine/)
24. Sennrich, R., Haddow, B., and Birch, A. (2016). Neural Machine Translation of Rare Words with Subword Units. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pages 1715–1725. [↗](https://doi.org/10.18653/v1/p16-1162)
25. Tafa, T., Hashim, S., Othman, M., Alhussian, H., Nasser, M., Jadid Abdulkadir, S., Huspi, S., Adeyemo, S., and Bena, Y. (2025). Machine Translation Performance for Low-Resource Languages: A Systematic Literature Review. IEEE Access, PP:1–1, 01. [↗](https://doi.org/10.1109/access.2025.3562918)
26. Tedla, Y. and Yamamoto, K. (2016). The Effect of Shallow Segmentation on English-Tigrinya Statistical Machine Translation. In 2016 International Conference on Asian Language Processing (IALP), page 20. IEEE, November. [↗](https://doi.org/10.1109/ialp.2016.7875939)
27. van Peursen, W., Naaijer, M., Sikkel, C., Coeckelbergs, M., and Attema, J. (2023). A Transformer-based Parser for Syriac Morphology. In Adam Anderson, et al., editors, Proceedings of the Ancient Language Processing Workshop, pages 23–29. Incoma Ltd. Publisher Copyright: © RANLP-ALP 2023 - Proceedings of the Ancient Language Processing Workshop, associated with 14th International Conference on Recent Advances in Natural Language Processing.; 1st Workshop on Ancient Language Processing, ALP 2023 ; Conference date: 08-09-2023. [find](https://scholar.google.com/scholar?q=van+Peursen%2C+W%2E%2C+Naaijer%2C+M%2E%2C+Sikkel%2C+C%2E%2C+Coeckelbergs%2C+M%2E%2C+and+Attema%2C+J%2E+%282023%29%2E+A+Transformer%2Dbased+Parser+for+Syriac+Morphology%2E+In+Adam+Anderson%2C+et+al%2E%2C+editors%2C+Proceedings+of+the+Ancient+Langu) [our card](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2023-naaijer-transformer-based-parser-syriac-morphology/)
28. Velayuthan, M., Jayakody, D., De Silva, N., Fernando, A., and Ranathunga, S. (2024). Back to the Stats: Rescuing Low Resource Neural Machine Translation with Statistical Methods. In Barry Haddow, et al., editors, Proceedings of the Ninth Conference on Machine Translation, pages 901–907, Miami, Florida, USA, November. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2024.wmt-1.87)