AI Meets Shakespeare: Translating Classical English into the Modern |
||
 |
 |
|
| © 2024 by IJCTT Journal | ||
| Volume-72 Issue-12 |
||
| Year of Publication : 2024 | ||
| Authors : Sandeep M Asokan | ||
| DOI : 10.14445/22312803/IJCTT-V72I12P112 | ||
How to Cite?
Sandeep M Asokan, "AI Meets Shakespeare: Translating Classical English into the Modern," International Journal of Computer Trends and Technology, vol. 72, no. 12, pp. 100-107, 2024. Crossref, https://doi.org/10.14445/22312803/IJCTT-V72I12P112
Abstract
Reading classical English literature in today’s modern context can pose significant challenges, primarily due to the evolution of language over centuries. Classical texts' words, phrases, and sentence structures often differ greatly from contemporary usage, making comprehension difficult for modern readers. This study proposes a novel solution using Machine Translation (MT) techniques to bridge this gap and simplify the understanding of classical writings. In this work, Shakespeare’s play The Tragedy of Julius Caesar has been chosen as a benchmark for classical English, given its historical significance and rich linguistic complexity. The Llama2 Chat variant, a sophisticated Large Language Model (LLM), translates Shakespearean English into contemporary language, preserving the original intent and meaning while making the text more accessible. The study not only examines the translation process but also delves into the critical parameters of the LLM that influence its performance, such as its ability to interpret context, handle ambiguities, etc. This research aims to contribute to both the appreciation of classical literature and the advancement of AI in language processing.
Keywords
AI literature, Literary prompt, Llama2, Machine translation, Prompt engineering.
Reference
[1] Yuan Gao, Ruili Wang, and Feng Hou, “How to Design Translation Prompts for ChatGPT: An Empirical Study,” Proceedings of the 6th ACM International Conference on Multimedia in Asia Workshops, New York, United States, pp. 1-7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Wenshi Gu, “Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses,” Arxiv Preprint, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] International Standard Organization (ISO), ISO/TS (2012) ISO 11669:2012 Translation Projects - General Guidance, 2012. [Online]. Available: https://www.iso.org/standard/50687.html
[4] ISO 17100: 2015, Translation Services - Requirements for Translation Services, International Standard Organization (ISO), 2015. [Online]. Available: https://www.iso.org/standard/59149.html
[5] Wenxiang Jiao et al., “Is ChatGPT a Good Translator? Yes, With GPT-4 As the Engine,” Arxiv Preprint, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yasmin Moslem et al., “Adaptive Machine Translation with Large Language Models,” Arxiv Preprint, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Eugene A. Nida, and R. Taber Charles, The Theory and Practice of Translation, Brill for United Bible Societies, 2003.
[Google Scholar] [Publisher Link]
[8] Masaru Yamada, and Nanami Onishi, Metalanguage for Translation Project Management, Routledge, 1st ed., pp. 50-62, 2021.
[Google Scholar] [Publisher Link]
[9] Anthony Pym, “Translation Error Analysis and the Interface with Language Teaching,” The teaching of translation, pp. 279-288, 1992.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Julius Caesar Translation, LitCharts, 2024. [Online]. Available: https://www.litcharts.com/shakescleare/shakespeare-translations/julius caesar