Neural Machine Translation Technique for Interpreting Ancient Texts in Philology Education

View at publisher Summarise with VIRAT
Authors: Hulkar Vasilovna OrMiHulkar Vasilovna Mirzakhmedova, Shuhrat Mirziyotov, Gavharoy Mannobjon kizi Kholisova, Islomjon Isroilovich Umrzaqov, Yana Davidovna Kuchkarova, N.M. Kadirova
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Neural Machine Translation (NMT) can be used as a transformative potential in the education of philology since it allows the automatic interpretation of ancient texts. The method contributes to the maintenance of linguistics and greater availability of classical knowledge. The methods that exist are, however, usually limited by certain problems, including limited parallel corpora, semantic ambiguity, and transfer of knowledge between poorly resourced ancient languages. To address such difficulties, the suggested framework uses Zero-Shot Translation Model (ZSTM), which utilizes multilingual embeddings and transfer learning to understand texts without having to deal with direct parallel data. This model helps to conduct crosslinguistic analysis, helps students to understand the archaic linguistic forms, and allows the real-time educational activities in the field of philology. The results reveal that ZSTM enhances the accuracy of translation, preserves cultural and semantic integrity, and improves the interest of the learners in the manuscripts of the past. In general, the method helps fill the gaps in philological studies and also provides a viable answer to the ancient language in the contemporary education.

Fields of Study & Subjects

Natural Language Processing Techniques Translation Studies and Practices Topic Modeling

Publication details

Journal / source
International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)
Pages
1–7
Publication date
8 January 2026
Language
EN