Towards the First Machine Translation System for Sumerian Transliterations

Punia, Ravneet; Schenk, Niko; Chiarcos, Christian; Pagé-Perron, Émilie

doi:10.18653/v1/2020.coling-main.308

Cited by 5 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first NMT results for texts written in Sumerian from the Ur III period (see Materials and methods ) are based on c. 10,000 transliteration to English translation sentences. They report the best BLEU scores with 2 different NMT models of 20.9 and 21.6 and the worst score with a statistical based model of 8.2 ( 15 ). Their best model was an attention LSTM model pretrained on English word embeddings from Wikipedia.…”

Section: Related Workmentioning

confidence: 99%

Translating Akkadian to English with neural machine translation

et al. 2023

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Translating Akkadian to English with neural machine translation

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This body of work has focused on optical character recognition and visual analysis [31][32][33][34] , writer identification [35][36][37] and text analysis [38][39][40][41][42][43][44] , stylometrics 45 and document dating 46 . It is only very recently that scholarship has begun to use deep learning and neural networks for optical character recognition [47][48][49][50][51][52][53][54][55] , text analysis 56 , machine translation of ancient texts [57][58][59] , authorship attribution 60,61 and deciphering ancient languages 62,63 , and been applied to study the form and style of epigraphic monuments 64 .…”

Section: Previous Workmentioning

confidence: 99%

Restoring and attributing ancient texts using deep neural networks

Assael

Sommerschield

Shillingford

et al. 2022

Nature

View full text Add to dashboard Cite

Ancient history relies on disciplines such as epigraphy—the study of inscribed texts known as inscriptions—for evidence of the thought, language, society and history of past civilizations1. However, over the centuries, many inscriptions have been damaged to the point of illegibility, transported far from their original location and their date of writing is steeped in uncertainty. Here we present Ithaca, a deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions. Ithaca is designed to assist and expand the historian’s workflow. The architecture of Ithaca focuses on collaboration, decision support and interpretability. While Ithaca alone achieves 62% accuracy when restoring damaged texts, the use of Ithaca by historians improved their accuracy from 25% to 72%, confirming the synergistic effect of this research tool. Ithaca can attribute inscriptions to their original location with an accuracy of 71% and can date them to less than 30 years of their ground-truth ranges, redating key texts of Classical Athens and contributing to topical debates in ancient history. This research shows how models such as Ithaca can unlock the cooperative potential between artificial intelligence and historians, transformationally impacting the way that we study and write about one of the most important periods in human history.

show abstract

“…Past work aimed at machine translation of Sumerian-English (Pagé-Perron et al, 2017;Punia et al, 2020a) have used the minimal bitext upon a variety of general statistical and neural supervised techniques. However, they do not handle the textlevel peculiarities any differently than one would do for a high-resource language, thus, often failing to capture context, resulting in poor and inconsistent translations.…”

Section: Related Workmentioning

confidence: 99%

“…We perform experiments on a variety of data configurations which are given by: 1. UrIIISeg: Follows the format as present in the original texts provided by Assyriologists and used in the past attempts for Sumerian-English machine translation (Pagé-Perron et al, 2017;Punia et al, 2020b). It contains only in-domain Ur III Admin text with line-by-line translated segments, each of 1-5 words.…”

Section: Supervised Nmtmentioning

confidence: 99%

How Low is Too Low? A Computational Perspective on Extremely Low-Resource Languages

Bansal¹,

Choudhary²,

Punia³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Despite the recent advancements of attentionbased deep learning architectures across a majority of Natural Language Processing tasks, their application remains limited in a lowresource setting because of a lack of pretrained models for such languages. In this study, we make the first attempt to investigate the challenges of adapting these techniques to an extremely low-resource language -Sumerian cuneiform -one of the world's oldest written language attested from at least the beginning of the 3rd millennium BC. Specifically, we introduce the first cross-lingual information extraction pipeline for Sumerian, which includes part-of-speech tagging, named entity recognition, and machine translation. We introduce InterpretLR, an interpretability toolkit for low-resource NLP and use it alongside human evaluations to gauge the trained models. Notably, all our techniques and most components of our pipeline can be generalised to any low-resource language. We publicly release all our implementations including a novel data set with domain-specific pre-processing to promote further research in this domain.2. 1(disz) kusz masz2 niga 1 hide, grain-fed goat;3. kusz udu sa2-du11 sheep hides, regular offerings, 4. ki {d}iszkur-illat-ta from Adda-illat, obverse.reverse.

show abstract

Towards the First Machine Translation System for Sumerian Transliterations

Cited by 5 publications

References 16 publications

Translating Akkadian to English with neural machine translation

Translating Akkadian to English with neural machine translation

Restoring and attributing ancient texts using deep neural networks

How Low is Too Low? A Computational Perspective on Extremely Low-Resource Languages

Contact Info

Product

Resources

About