# DANES Newsletter - December 2023

## Table of Contents

- [Additions to DANES Resources](#additions-to-danes-resources)
- [DANES Working Groups](#danes-working-groups)
- [Recent Academic Publications](#recent-academic-publications)
- [Datasets Published](#datasets-published)
- [Conferences and Call for Papers](#conferences-and-call-for-papers)

## <a id="additions-to-danes-resources">Additions to DANES Resources</a>

We would like to thank members of our community who contributed to the DANES Resources this month:

* Robin Leroy, who contributed the Enmerkar (𒂗𒈨𒅕𒃸) tool, a downloadable keyboard for typing cuneiform characters, compatible with Windows and Mac.
* Carlos Gracia Zamacona, who contributed MORTEXVAR, a database which collects data on ancient Egyptian Coffin Texts to digitise, analyse, and make them accessible.

Also, six more resources were added, including the [Epigraphische Datenbank zum antiken Kleinasien](https://www.epigraphik.uni-hamburg.de/content/index.xml), [Hieratic Studies Online](https://aku.uni-mainz.de/hieratic-studies-online/), [Opera Latina Adnotata](https://git.informatik.uni-leipzig.de/celano/latinnlp/-/tree/master), [Fast(Text) Analysis of Mesopotamian Divine Names](https://doi.org/10.5281/zenodo.7494289), [eHammurabi](https://ehammurabi.com/), and the [Nineveh Tablet Collection](https://fincke-cuneiform.com/nineveh/index.htm).

## <a id="danes-working-groups">DANES Working Groups</a>

### OCR working group

On **Monday 4^th of December** (16:00 CET / 17:00 IST / 10:00 EST), Yunus Cobanoglu (LMU Munich, Germany) will give an online talk on _Revolutionizing Archaeology with AI - Decoding the Past through Automated Cuneiform Sign Recognition_. Yunus’ talk continues on what he presented at [DANES 2023](https://youtu.be/4JxIGMZt4TM?feature=shared). The talk will take place [via zoom](https://ariel-ac-il.zoom.us/j/89304918190?pwd=LzduZUUzR3ZydXRPK0FhWVNPSzVJdz09).

short Bio:

Yunus Cobanoglu studied Computer Science and Computer Linguistics as an undergraduate in the Ludwig-Maximilians-University where he received his Bachelor Degree in 2019. He received his Master Degree in Mathematics from Technical University in Munich in 2023. Since 2019 he has been a Member at the Institute of Assyriology and the Electronic Babylonian Library Project.

### MEGA-ALP Elamite task force

This workshop is planned to give participants a practical experience on how to create a framework for the digital study of under-resourced ANE languages, focusing on Elamite as a case-study. 29 students and scholars from eight countries and different backgrounds signed up to participate! More are still welcomed to join.

The first meeting on the 29^th of November was an introduction to the ideas, goals and aims, and methodologies to be employed by the task force for creating digital resources for Elamite, from a lemma base to an annotated textual corpus. The slides used for the first meeting and the recording are available through the [task force’s organizational document](https://docs.google.com/document/d/1RSrpWYOjYBfNRAzjW7mPE9txhAeH8mee/edit?usp=sharing&ouid=105840067147853910357&rtpof=true&sd=true).

This month the meeting will take place earlier on **Wednesday 13^th of December**, to allow everyone a restful Christmas. We will meet at 15:00-17:00 CET / 16:00-18:00 IST / 09:00-11:00 EST. Together, we design an ontology for the Elamite lemma base, and a hands-on session on data pre-processing and cleaning!

### The DANES happy-hour

A get-together on the DANES discord channel to discuss news in computational studies of the ANE, following up on the monthly newsletter.

The meeting will be on the first Wednesday of the month, **December 6^th 2024** 17:00-18:00 CET / 18:00-19:00 IST / 11:00-12:00 EST. Come one and all to the DANES Discord happy-hour channel!

[](https://commons.wikimedia.org/wiki/File:Athenian_inscription_in_commemoration_of_victories_over_the_Persians_490-480_BC._Ancient_Agora_Museum_of_Athens.jpg)

## <a id="recent-academic-publications">Recent Academic Publications</a>

**[Proceedings of the Fourth Computational Humanities Research Conference 2023](https://ceur-ws.org/Vol-3558/), Edited by Artjoms Šeļa, Fotis Jannidis, and Iza Romanowska**

The Computational Humanities Research (CHR) conference is a leading venue for the presentation and publication of application of computational methodologies to all fields of the humanities. It aims to build a community of scholars and promote best practices in digital humanities.

The fourth conference will take place on [December 6-8, 2023 in Paris at the École pour l’informatique et les techniques avancées](https://2023.computational-humanities-research.org/). The conference proceedings are already published after peer review, following practices of conferences in computer science.

The proceedings include case-studies ranging from historical to contemporaneous periods, or methodologically centered articles on best-practice implementations of state-of-the-art technologies. Some of the proceedings are on topics particularly relevant to the DANES community, such as:

**[Enhancing HTR of Historical Texts through Scholarly Editions: A Case Study from an Ancient Collation of the Hebrew Bible](https://ceur-ws.org/Vol-3558/paper6310.pdf), by Luigi Bambaci and Daniel Stökl Ben Ezra**

Handwritten Text Recognition (HTR) is vital for the digitization of historical sources, usually done today with state-of-the-art Optical Character Recognition (OCR) models. This article provides a case-study into the digitization efforts of the _Vetus Testamentum hebraicum cum variis lectionibus_ by Benjamin Kennicott, written in the 18th century CE. It is a collation of the Hebrew Bible created from 600 manuscripts and containing an extensive critical apparatus. The authors describe the different existing models they used for automatic layout detection and text recognition, and then manual corrections and rule-based reconstructions of the different manuscripts underlying the work. The latter can then be used for image-to-text alignment on the images of the original Hebrew manuscripts. Their work shows the high-applicability of using existing models for ancient sources: they achieved extremely productive results of 97-98% accuracy for the different stages in their pipeline. It is also an important example of how to design a beginning-to-end pipeline from print scholarly edition to digital scholarly edition using best-practice modern formats and tools.

**[Testing the Limits of Neural Sentence Alignment Models on Classical Greek and Latin Texts and Translations](https://ceur-ws.org/Vol-3558/paper6193.pdf), by Caroline Craig, Kartik Goyal, Gregory Crane, Farnoosh Shamsian, and David A. Smith**

This article quantifies the challenges and potential of automatic sentence and word alignment between ancient texts and their modern translation. Sentence or word alignment between the source and target languages are fundamental prerequisites for translations powered by AI, as well as computational studies of variations in translations and changes in cultural assumptions and interpretations. This alignment is necessary for many other applications in natural language processing (NLP) as well. The authors of this study use an annotated corpus of source texts in Latin and Ancient Greek with their translations into English, French, German, and Persian to find the best pipeline from currently available models for automatically aligning source and target languages. They discuss the potential and downsides of their pipeline and future improvements of their models.

[](https://lila-erc.eu/data/id/lemma/91435)

## <a id="datasets-published">Datasets Published</a>

**[Journal of Open Humanities Data](https://openhumanitiesdata.metajnl.com/): Representing the Ancient World through Data**

Open Humanities Data journal publishes peer reviewed descriptions of research techniques or dataset descriptions. Last June, they released a call for papers for a special collection of publications of datasets from the ancient world. Accepted publications have been gradually released this month, with _more to come in the following months_. These include:

**[The Database of Hellenistic Inscribed Epigrams from Doric-speaking Areas](https://openhumanitiesdata.metajnl.com/articles/10.5334/johd.134), by Dalia Pratali Maffei**

Published a dataset in which each inscription appears with an ID, edition, provenance, date, type, and more. The data was created manually based on previous publications. It is the first collection of inscriptions from Doric-speaking areas specifically.

**[The LiLa Lemma Bank: A Knowledge Base of Latin Canonical Forms](https://openhumanitiesdata.metajnl.com/articles/10.5334/johd.145), by Francesco Mambrini, Marco Carlo Passarotti**

Published a linguistic linked open dataset of 215,102 Latin lemma forms, which includes morphological properties. It was created as part of the _LiLa: Linking Latin_ project, to link together corpora and dictionaries.

**[Lost at Sea: A Dataset of 25+ SEA Words Morpho-Semantically Annotated in Ancient Greek and Latin](https://openhumanitiesdata.metajnl.com/articles/10.5334/johd.139), by Andrea Farina**

Published annotations in-context of more than 25 words in Ancient Greek and Latin that are related to the sea or sea-faring. The texts chosen for annotations are De Bello Gallico by Caesar, Aeneid 1–6 by Vergil, Histories 1–2 by Herodotus, and Argonautica by Apollonius Rhodius. This dataset can be used for further linguistic and semantic studies.

**[The Mesopotamian Ancient Place-Names Almanac (MAPA): A Gazetteer of the Uruk Urbanscape in the Age of Empires](https://openhumanitiesdata.metajnl.com/articles/10.5334/johd.146), by Shmuel Clark, Shai Gordin**

Published the MAPA gazetteer, a linked open dataset that currently includes almost 400 placenames attested in legal, economic, and administrative documents from the city Uruk, dated to the first millennium BCE. It includes, among others, descriptions of types of placenames, variant spellings, and connections between placenames.

**[Translation Alignment for Ancient Greek: Annotation Guidelines and Gold Standards](https://openhumanitiesdata.metajnl.com/articles/10.5334/johd.131), by Chiara Palladino, Farnoosh Shamsian, Tariq Yousef, David J. Wright, Anise d’Orange Ferreira, Michel Ferreira dos Reis**

Published aligned annotations of ancient Greek to English, Portuguese, and Latin. The alignments were performed manually by experts to ensure quality. It also includes an annotation style guide to maintain standards for future annotations. The dataset is meant to be used for training machine learning models.

**[Word Lengths in Classical and Post-Classical Greek](https://openhumanitiesdata.metajnl.com/articles/10.5334/johd.121), by Mathilde Bru**

Published a dataset of words and word lengths from a sample of classical Greek from the 5^th century BCE and a sample of 1^st century CE Greek. It includes statistical measures of word lengths, which demonstrates average word lengths in Greek increased significantly between the periods under study.

[](https://commons.wikimedia.org/wiki/File:Pergamonmuseum_-_Antikensammlung_-_Vase_10.JPG)

## <a id="conferences-and-call-for-papers">Conferences and Call for Papers</a>

### Upcoming Events

**The [9th Linked Pasts Symposium](https://linkedpasts.hcommons.org/) (Dec 4–15)** is an online-only series of activities running for the first two weeks of December. Activities include working groups and workshops, like linked open data for non-Western concepts, a digital Classicist Wiki sprint working with Peripleo and Recogito, both robust tools for geographic annotation and visualization, and a CDLI workshop for Assyriologists and those interested in computational work on metadata and collections. To consult the program and register visit the following [link](https://linkedpasts.hcommons.org/2023/11/17/linked-pasts-9-programme/).

**The [Digital Classicist Berlin seminar](https://digiclass.bbaw.de/seminar.html) series** for 2023/24 will deal with the use of AI in the study of the Ancient World. It will take place on every second Tuesday at 16:00 CET and be broadcasted [via Zoom](https://hu-berlin.zoom.us/j/68772389150?pwd=S1RkWWZtYU9zaXZLWTA5OFVJb2FVUT09).

Planned talks for December 2023 include Claudia Antonetti and Eloisa Paganoni on _Preserving Inscriptions on Paper: Old and New Challenges. The Experience of the Venice Squeeze Project_ (**Dec 5**); and G. R. Smidt, E. Lefever, K. De Graef, K. K. T. Chandrasekar, L. Foket on _MIND THE GAP! Advancing Cuneiform Studies through Digital Collaboration_ (**Dec 19**).

**The [2023/24 Digital History research colloquium of the Humboldt University](https://dhistory.hypotheses.org/digital-history-forschungskolloquium/wintersemester-2023-2024) of Berlin** hosts lectures on data modeling, linked open data and AI applications for historical data and research questions. Noteworthy in December is Ingo Frank on _Ontology Design Patterns for History: Modeling Place-based Information in the Digital Map Lab Holy Roman Empire_ (**Dec 6**).

**[Fourth Computational Humanities Research Conference](https://2023.computational-humanities-research.org)** **(Dec 6-8, Paris and online)** The Computational Humanities Research (CHR) conferences aim to build a community of scholars in this field and promote best practices. The conference proceedings were already published (see above). Registration is still possible for online participants for a fee.

**[Trust Issues. Artificial Intelligence, Human Cognition, and Archaeology](https://www.uni-augsburg.de/de/fakultaet/philhist/professuren/kunst-und-kulturgeschichte/klassische-archaologie/forschung/trust-issues-artificial-intelligence-human-cognition-and-archaeo/)** **(Dec 8, Augsburg Germany and online via zoom)** will address pitfalls and opportunities of using AI for archaeological research, such as developing trustworthy AI, transparency and accountability, and integrating human cognitive skills with AI technologies. Presentations include methodological considerations, case-studies, and collaborative work and dialogues.

**[Machine Learning in Archaeology: An introduction to concepts and practical applications](https://www.icarehb.com/icarhub/tifa/machine-learning/) (5-7 March 2024, registration by Dec 17)** is a three day immersive introductory course for applying machine learning for archaeology. It will include theoretical lectures and hands-on sections, and will take place in person at the University of Algarve, Faro, Portugal. It is aimed for archaeologists in all career stages from MA students to postdoctoral researchers. The course instructors are Dr. Alex Brandsen and Prof. Dr. Björn Menze. <span style="text-decoration:underline;">Deadline for registration is December 17</span>. There is a registration fee and costs are not covered.

### Call for Papers

**[Digital Humanities Summer Institute](https://dhsi.org/aligned-events-2024/) 2024** is the one of the largest annual conferences for digital humanities. It is a two weeks’ conference set to take place 3-14 June 2024 in Victoria University, Canada. DHSI hosts conference talks, colloquia, and courses on a variety of topics, including for beginner levels. They have released their call for conference presentations and colloquium lightning talks. The deadline for submitting abstracts is <span style="text-decoration:underline;">December 15^th 2023</span>.

---------------------------------

[](https://collections.peabody.yale.edu/search/Record/YPM-BC-010682)

Did we miss relevant articles published in the previous month? Did we miss upcoming events in the next month? Would you like to ensure your news will appear in the next newsletter? Please send us an email at [[e-mail]](mailto:[e-mail])! Corrections to published Newsletters will be sent via the DANES mailing list.