Restoring Gilgamesh Through AI With a Negotiation Algorithm Approach
DOI:
https://doi.org/10.17507/tpls.1410.05Keywords:
negotiation algorithm approach, Gilgamesh, missing lines, restorationAbstract
In this study, the AI tool ChatGPT is utilised to enhance Tablet 2 of the Epic of Gilgamesh by using a perfected approach for restoration. The proposed negotiation algorithm regulates the interaction of ChatGPT with a human expert and ensures that the words generated are stylistically suitable. ChatGPT employs an interactive scheme, proposing different alternatives for each missing line, and the human specialist evaluates these alternatives in terms of their coherence, consistency, and adherence to the story. The expert evaluation is the key factor in the improvement of the text generation process, as this evaluation increases the restoration efficiency. This combination of AI and human intelligence, in turn, refines Tablet 2 by obtaining more accurate paragraphs and, thus, making the restoration more appropriate. Through this model, ChatGPT not only helps with the comprehension of the epic but also provides new insights into the work’s literary and historical importance. The negotiation algorithm is an outstanding method that may provide a better understanding of the whole work by providing new insights. This study reveals the possibility of using the collaboration between AI and human thinking in the field of literary restoration, which represents a new direction for understanding and enjoying ancient literary texts.
References
Al-Rfou, R., Perozzi, B., & Skiena, S. (2018). Kugler: A knowledge-guided framework for text generation. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 506-517.
Artstein, R., & Poesio, M. (2008). Inter-annotator agreement in computational linguistics. Computational Linguistics, 34(4), 555-596.
Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python. O'Reilly Media, Inc.
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL-HLT, 4171-4186.
George, A. R. (2003). The Epic of Gilgamesh: A New Translation. Penguin Books.
Jurafsky, D., & Martin, J. H. (2021). Speech and language processing (3rd ed.). Pearson.
Kovacs, M. G. (2018). The Epic of Gilgamesh. Stanford University Press.
Lafferty, J., McCallum, A., & Pereira, F. (2001). Conditional random fields: probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning (ICML-2001), 282-289.
Manning, C. D., & Schütze, H. (1999). Foundations of statistical natural language processing. MIT press Cambridge.
Manning, C. D., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S., & McClosky, D. (2014). The Stanford CoreNLP natural language processing toolkit. In Association for Computational Linguistics (ACL) System Demonstrations, 55-60.
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of Word representations in vector space. ArXiv preprint arXiv :1301.3781.
Mitchell, T. C. (2004). The Epic of Gilgamesh: A new translation with commentary. W. W. Norton & Company.
Osborne, M. J., & Rubinstein, A. (1990). Bargaining and markets. Academic Press.
Parpola, S. (1997). The Standard Babylonian Epic of Gilgamesh. Neo-Assyrian Text Corpus Project.
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2022). Language models are few-shot learners. Neural Information Processing Systems, 35, 9741-9755.
Zadrozny, W., & Elhadad, N. (2009). Incorporating expert knowledge into machine learning for text classification. Machine Learning, 75(3), 257-281.
