Machine Translation for Historical Research: A case study of Aramaic-Ancient Hebrew Translations-Reference-Cited by-同舟云学术

Machine Translation for Historical Research: A case study of Aramaic-Ancient Hebrew Translations

Published:2023-10-16 Issue: Volume: Page:
ISSN:1556-4673
Container-title:Journal on Computing and Cultural Heritage
language:en
Short-container-title:J. Comput. Cult. Herit.

Author:

Liebeskind Chaya¹,Liebeskind Shmuel²,Bouhnik Dan¹

Affiliation:

1. Department of Computer Science, Jerusalem College of Technology, Israel

2. Department of Data Mining, Jerusalem College of Technology, Israel

Abstract

In this article, by the ability to translate Aramaic to another spoken languages, we investigated Machine Translation (MT) in a cultural heritage domain for two primary purposes: evaluating the quality of ancient translations and preserving Aramaic (an endangered language). First, we detailed the construction of a publicly available Biblical parallel Aramaic-Hebrew corpus based on two ancient (early 2 nd - late 4 th century) Hebrew–Aramaic translations: Targum Onkelus and Targum Jonathan. Then using the Statistical Machine Translation (SMT) approach, which in our use-case significantly outperforms the Neural Machine Translation (NMT), we validated the excepted high quality of the translations. The trained model failed to translate Aramaic texts of other dialects. However, when we trained the same SMT model on another Aramaic-Hebrew corpus of a different dialect (Zohar - 13 th century) a very high translation score was achieved. We examined an additional important cultural heritage source of Aramaic texts, the Babylonian Talmud (early 3 rd - late 5 th century). Since we do not have a parallel Aramaic-Hebrew corpus of the Talmud, we used the model trained on the Bible corpus for translation. We performed an analysis of the results and suggest some potential promising future research.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design,Computer Science Applications,Information Systems,Conservation

Link

https://dl.acm.org/doi/pdf/10.1145/3627168

Reference137 articles.

1. David Ifeoluwa Adelani Dana Ruiter Jesujoba O Alabi Damilola Adebonojo Adesina Ayeni Mofetoluwa Adeyemi Ayodele Awokoya and Cristina España-Bonet. 2021. MENYO-20k: A multi-domain english-yorubá corpus for machine translation and domain adaptation. CoRR abs/2103.08647(2021). David Ifeoluwa Adelani Dana Ruiter Jesujoba O Alabi Damilola Adebonojo Adesina Ayeni Mofetoluwa Adeyemi Ayodele Awokoya and Cristina España-Bonet. 2021. MENYO-20k: A multi-domain english-yorubá corpus for machine translation and domain adaptation. CoRR abs/2103.08647(2021).

2. Orevaoghene Ahia Julia Kreutzer and Sara Hooker. 2021. The low-resource double bind: An empirical study of pruning for low-resource machine translation. arXiv preprint arXiv:2110.03036(2021). Orevaoghene Ahia Julia Kreutzer and Sara Hooker. 2021. The low-resource double bind: An empirical study of pruning for low-resource machine translation. arXiv preprint arXiv:2110.03036(2021).

3. Alham Fikri Aji , Nikolay Bogoychev , Kenneth Heafield , and Rico Sennrich . 2020 . In Neural Machine Translation, What Does Transfer Learning Transfer? . In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 7701–7710 . https://doi.org/10.18653/v1/2020.acl-main.688 10.18653/v1 Alham Fikri Aji, Nikolay Bogoychev, Kenneth Heafield, and Rico Sennrich. 2020. In Neural Machine Translation, What Does Transfer Learning Transfer?. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 7701–7710. https://doi.org/10.18653/v1/2020.acl-main.688

4. Philip S Alexander . 1992 . ”Targum, Targumim”. Anchor Bible Dictionary 6 (1992), 320 – 331 . Philip S Alexander. 1992. ”Targum, Targumim”. Anchor Bible Dictionary 6 (1992), 320–31.

5. David Alvarez-Melis and Tommi Jaakkola . 2017 . A causal framework for explaining the predictions of black-box sequence-to-sequence models . In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 412–421 . David Alvarez-Melis and Tommi Jaakkola. 2017. A causal framework for explaining the predictions of black-box sequence-to-sequence models. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 412–421.