Machine Translation and Automated Analysis of the Sumerian Language

Pagé-Perron, Émilie; Sukhareva, Maria; Khait, Ilya; Chiarcos, Christian

doi:10.18653/v1/w17-2202

Cited by 17 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, a sign detector might fuse detections from 2D images from different angles of a clay tablet in order to deal with difficult cases. Similarly, if language models for cuneiform script become available in the future and problems like data sparsity are overcome [50], their integration will also help with ambiguous detections.…”

Section: Discussionmentioning

confidence: 99%

Deep learning of cuneiform sign detection with weak supervision using transliteration alignment

et al. 2020

View full text Add to dashboard Cite

The cuneiform script provides a glimpse into our ancient history. However, reading age-old clay tablets is time-consuming and requires years of training. To simplify this process, we propose a deep-learning based sign detector that locates and classifies cuneiform signs in images of clay tablets. Deep learning requires large amounts of training data in the form of bounding boxes around cuneiform signs, which are not readily available and costly to obtain in the case of cuneiform script. To tackle this problem, we make use of existing transliterations, a sign-by-sign representation of the tablet content in Latin script. Since these do not provide sign localization, we propose a weakly supervised approach: We align tablet images with their corresponding transliterations to localize the transliterated signs in the tablet image, before using these localized signs in place of annotations to re-train the sign detector. A better sign detector in turn boosts the quality of the alignments. We combine these steps in an iterative process that enables training a cuneiform sign detector from transliterations only. While our method works weakly supervised, a small number of annotations further boost the performance of the cuneiform sign detector which we evaluate on a large collection of clay tablets from the Neo-Assyrian period. To enable experts to directly apply the sign detector in their study of cuneiform texts, we additionally provide a web application for the analysis of clay tablets with a trained cuneiform sign detector.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning of cuneiform sign detection with weak supervision using transliteration alignment

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This is the only related work we are aware of in which cuneiform texts encoded in Unicode cuneiform have been processed previous to our experiments. Pagé-Perron et al (2017) present a project dedicated to creating a pipeline for Sumerian texts. The pipeline is planned to take in transliterated Sumerian and to produce POS tag annotations and lemmatization as well as machine translation into English.…”

Section: Cuneiform Script and Computational Methodsmentioning

confidence: 99%

Language and Dialect Identification of Cuneiform Texts

Jauhiainen¹,

Jauhiainen

Alstola

et al. 2019

Proceedings of the Sixth Workshop On

View full text Add to dashboard Cite

This article introduces a corpus of cuneiform texts from which the dataset for the use of the Cuneiform Language Identification (CLI) 2019 shared task was derived as well as some preliminary language identification experiments conducted using that corpus. We also describe the CLI dataset and how it was derived from the corpus. In addition, we provide some baseline language identification results using the CLI dataset. To the best of our knowledge, the experiments detailed here represent the first time that automatic language identification methods have been used on cuneiform data.

show abstract

“…Homburg and Chiarcos (2016) report preliminary results on automatic word segmentation for Akkadian cuneiform using rule-based, dictionary based, and data-driven statistical techniques. Pagé-Perron et al (2017) furnish an analysis of Sumerian text including morphology, parts-ofspeech (POS) tagging, syntactic parsing, and machine translation using a parallel corpus. Although Sumerian and Akkadian are both geographically and chronologically close to PE, these corpora are very large (e.g.…”

Section: Lda Summarymentioning

confidence: 99%

Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature

2019

View full text Add to dashboard Cite

Welcome to the third edition of LaTeCH-CLfL-which also is the thirteenth edition of LaTeCH and eighth of CLfL. We have had fun preparing the workshop, and we will be happy if you have fun attending (or at least reading the workshop papers:). Please visit the website at https://sighum.wordpress.com/events/latech-clfl-2019/ where you will find the workshop presentations, among other things. The papers cover, as usual, topics which you will not easily find at regular NLP conferences. The authors take on literary texts, including drama and poetry, and more generally literary study; historical texts; ancient or otherwise old languages; government documents; code switching; and more. Last but certainly not least, we will have an invited talk. Ian Milligan, a historian, has a deep interest in Digital Humanities, and understands the role on Natural Language Processing in his discipline. It is our pleasant duty to thank the authors: there would be no workshop without you. Nor without the program committee, to whom we are ever so grateful for their thorough and helpful reviews.

show abstract

Machine Translation and Automated Analysis of the Sumerian Language

Cited by 17 publications

References 9 publications

Deep learning of cuneiform sign detection with weak supervision using transliteration alignment

Deep learning of cuneiform sign detection with weak supervision using transliteration alignment

Language and Dialect Identification of Cuneiform Texts

Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature

Contact Info

Product

Resources

About