Exploring geomagnetic variations in ancient mesopotamia: Archaeomagnetic study of inscribed bricks from the 3rd-1st millennia BCE.

This study presents 32 high-resolution geomagnetic intensity data points from Mesopotamia, spanning the 3rd to the 1st millennia BCE. These data contribute to rectifying geographic disparities in the resolution of the global archaeointensity curve that have hampered our understanding of geomagnetic field dynamics and the viability of applying archaeomagnetism as a method of absolute dating of archaeological objects. A lack of precise and well-dated intensity data in the region has also limited our ability to identify short-term fluctuations in the geomagnetic field, such as the Levantine Iron Age geomagnetic Anomaly (LIAA), a period of high field intensity from ca. 1050 to 550 BCE. This phenomenon has hitherto not been well-demonstrated in Mesopotamia, contrary to predictions from regional geomagnetic models. To address these issues, this study presents precise archaeomagnetic results from 32 inscribed baked bricks, tightly dated to the reigns of 12 Mesopotamian kings through interpretation of their inscriptions. Results confirm the presence of the high field values of the LIAA in Mesopotamia during the first millennium BCE and drastically increase the resolution of the archaeointensity curve for the 3rd-1st millennia BCE. This research establishes a baseline for the use of archaeomagnetic analysis as an absolute dating technique for archaeological materials from Mesopotamia.

Translating Akkadian to English with neural machine translation.

Cuneiform is one of the earliest writing systems in recorded human history (ca. 3,400 BCE-75 CE). Hundreds of thousands of such texts were found over the last two centuries, most of which are written in Sumerian and Akkadian. We show the high potential in assisting scholars and interested laypeople alike, by using natural language processing (NLP) methods such as convolutional neural networks (CNN), to automatically translate Akkadian from cuneiform Unicode glyphs directly to English (C2E) and from transliteration to English (T2E). We show that high-quality translations can be obtained when translating directly from cuneiform to English, as we get 36.52 and 37.47 Best Bilingual Evaluation Understudy 4 (BLEU4) scores for C2E and T2E, respectively. For C2E, our model is better than the translation memory baseline in 9.43, and for T2E, the difference is even higher and stands at 13.96. The model achieves best results in short- and medium-length sentences (c. 118 or less characters). As the number of digitized texts grows, the model can be improved by further training as part of a human-in-the-loop system which corrects the results.

Reading Akkadian cuneiform using natural language processing.

In this paper we present a new method for automatic transliteration and segmentation of Unicode cuneiform glyphs using Natural Language Processing (NLP) techniques. Cuneiform is one of the earliest known writing system in the world, which documents millennia of human civilizations in the ancient Near East. Hundreds of thousands of cuneiform texts were found in the nineteenth and twentieth centuries CE, most of which are written in Akkadian. However, there are still tens of thousands of texts to be published. We use models based on machine learning algorithms such as recurrent neural networks (RNN) with an accuracy reaching up to 97% for automatically transliterating and segmenting standard Unicode cuneiform glyphs into words. Therefore, our method and results form a major step towards creating a human-machine interface for creating digitized editions. Our code, Akkademia, is made publicly available for use via a web application, a python package, and a github repository.

Restoration of fragmentary Babylonian texts using recurrent neural networks.

The main sources of information regarding ancient Mesopotamian history and culture are clay cuneiform tablets. Many of these tablets are damaged, leading to missing information. Currently, the missing text is manually reconstructed by experts. We investigate the possibility of assisting scholars, by modeling the language using recurrent neural networks and automatically completing the breaks in ancient Akkadian texts from Achaemenid period Babylonia.