Using Quantum Machine Learning to Resolve Ambiguity in Aramaic
Abstract
This paper studies the semantic ambiguity inherent in Ancient Aramaic from polysemy. To fix the loss of nuance in translations, we used a new framework based on Quantum Natural Language Processing (QNLP). It uses Variational Quantum Machine Learning (VQML) with a 10-qubit architecture and 300 optimization cycles. The model found a temporal-hierarchical interpretation for qaddamay with a confidence level of 96.15%. In contrast, Bar had a confidence level of 34.5% due to the scarcity of data in ancient corpora. This work connects quantum algorithms to more transparency in the study of historical manuscripts.
Fields of Study & Subjects
Quantum Computing Algorithms and Architecture
Natural Language Processing Techniques
Digital Humanities and Scholarship
Publication details
- Journal / source
- European Journal of Applied Science Engineering and Technology
- Volume
- 4
- Issue
- 2
- Pages
- 17–24
- Publication date
- 23 February 2026
- Language
- EN