Centre of Excellence in Artificial Intelligence for Digital Humanities

Informazioni relative al progetto

AI4DH

ID dell’accordo di sovvenzione: 101186647

DOI

10.3030/101186647

Data della firma CE 4 Novembre 2024

Data di avvio 1 Febbraio 2025

Data di completamento 31 Gennaio 2030

Finanziato da

• Widening participation and spreading excellence

Costo totale

Nessun dato

Contributo UE

€ 2 500 000,00

Coordinato da

UNIVERZA V LJUBLJANI
Slovenia

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Data Management Plan (1)

Data Management Plan - Initial

The initial version of the Data Management Plan (DMP). DMP outlines the strategies for handling research data, including data collection, storage, protection, sharing, and archiving, ensuring compliance with ethical standards and promoting open access and reuse.

Documents, reports (3)

Ethics, Quality and Risk Management Plan

The Initial Code of Ethics and a plan for Quality and Risk Management. The Code of Ethics establishes the principles and guidelines for ethical conduct and decision-making in the project, while the Quality and Risk Management Plan outlines the procedures for ensuring project quality, mitigating risks, and managing uncertainties to achieve project objectives effectively.

Centre of Excellence Functioning - Initial

The initial report on CoE functioning covers the establishment of the CoE. It presents the report on the first recruitment of post-doctoral researchers and PhD students, training and support for digital humanities scholars, project development support, and use of AI infrastructure.

MSc Module Curriculum

The report contains the curriculum for a master-level module in the MSc program at UL FCIS. The topic of the module will cover AI for DH contents. The curriculum contains the necessary elements so that the modulo can be accredited and implemented in the MSc study at UL.

Websites, patent fillings, videos etc. (1)

AI4DH website

The website describes the project and its main results. The initial version will be regularly updated.

Pubblicazioni

Conference proceedings (6)

Advancing interdisciplinary research: The European Centre of Excellence in Artificial Intelligence for Digital Humanities (CoE AI4DH)

Autori: Špela Arhar Holdt, Tinca Lukan, Kaja Dobrovoljc, Antoine Doucet, Simon Krek, Ajda Pretnar-Žagar, Polona Tratnik, Igor Vobič, Slavko Žitnik and Marko Robnik-Šikonja
Pubblicato in: AI in Science Summit 2025: 3.–4. November 2025, Copenhagen, Denmark, 2025
Editore: University of Copenhagen

Evaluating Robustness of LLMs in Question Answering on Multilingual Noisy OCR Data

Autori: Bhawna Piryani, Jamshid Mozafari, Abdelrahman Abdallah, Antoine Doucet, Adam Jatowt
Pubblicato in: Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025
Editore: ACM
DOI: 10.1145/3746252.3761295

Improving LLMs for machine translation using synthetic preference data

Autori: VAJDA, Dario, VREŠ, Domen, ROBNIK ŠIKONJA, Marko
Pubblicato in: Language understanding in the human machine era 2025 : proceedings of 2nd LUHME Workshop : Bologna, Italy, October 26, 2025. Porto: Universidade do Porto [etc.], 2025, 2025
Editore: Published by UP- Universidade do Porto (https://www.up.pt) LIACC- Laboratório de Inteligência Artificial e Ciência de Computadores da Universidade do Porto CLUP- Centro de Linguística da Universidade do Porto UEF- The University of Eastern Finland UAH
DOI: 10.21747/978-989-9193-73-4/LAN2

TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning

Autori: Kristian Miok, Blaz Škrlj, Daniela Zaharie, Marko Robnik Šikonja
Pubblicato in: Communications in Computer and Information Science, Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2026
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-032-19105-2_35

DELTA: A Toolkit for Measuring Linguistic Diversity in Dependency-Parsed Corpora

Autori: Louis Estève, Kaja Dobrovoljc
Pubblicato in: Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations), 2026
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2026.EACL-DEMO.6

Beyond CER and WER: How Does OCR Really Impact Information Retrieval?

Autori: Alexandre Jaud, Ahmed Hamdi, Antoine Doucet, Adam Jatowt, Mickaël Coustaty
Pubblicato in: 2025 ACM/IEEE Joint Conference on Digital Libraries (JCDL), 2026
Editore: IEEE
DOI: 10.1109/JCDL67857.2025.00014

Book chapters (2)

Rethinking OCR Evaluation for Information Extraction in Business Documents

Autori: Ngoc Nhi Nguyen, Ahmed Hamdi, Antoine Doucet, Adam Jatowt, Mickaël Coustaty
Pubblicato in: Lecture Notes in Computer Science, Intelligence and Equity: Shaping the Future of Knowledge, 2025
Editore: Springer Nature Singapore
DOI: 10.1007/978-981-95-4861-3_21

Ar-Q-Former: Historical Newspaper Article Separation Based on Multimodal Transformer Structure

Autori: Wenjun Sun, Nancy Girdhar, Hanh Thi Hong Tran, Carlos-Emiliano González-Gallardo, Mickaël Coustaty, Antoine Doucet
Pubblicato in: Lecture Notes in Computer Science, Document Analysis and Recognition – ICDAR 2025, 2025
Editore: Springer Nature Switzerland
DOI: 10.1007/978-3-032-04624-6_28

Peer reviewed articles (10)

Uporaba strojnega učenja za napovedovanje spola na poznoantičnem grobišču Lajh v Kranju = Applying machine learning to sex prediction at the late antique cemetery Lajh in Kranj

Autori: Pavletič, Kaja ; Pretnar Žagar, Ajda
Pubblicato in: Arheo : arheološka obvestila : glasilo Slovenskega arheološkega društva, Numero 42, 2025, ISSN 0351-5958
Editore: SAD Slovensko Arheološko društvo
DOI: 10.5281/ZENODO.17897796

Carniolan Provincial Assembly

Autori: Ajda Pretnar Žagar, Kristina Pahor de Maiti Tekavčič
Pubblicato in: Digital Humanities in the Nordic and Baltic Countries Publications, Numero 8, 2026, ISSN 2704-1441
Editore: University of Oslo Library
DOI: 10.5617/DHNBPUB.13202

Extreme Multi-Label Text Classification for Less-Represented Languages and Low-Resource Environments: Advances and Lessons Learned

Autori: Nikola Ivačič, Blaž Škrlj, Boshko Koloski, Senja Pollak, Nada Lavrač, Matthew Purver
Pubblicato in: Machine Learning and Knowledge Extraction, Numero 7, 2025, ISSN 2504-4990
Editore: MDPI AG
DOI: 10.3390/MAKE7040142

Retrieval-augmented code completion for local projects using large language models

Autori: Marko Hostnik, Marko Robnik-Šikonja
Pubblicato in: Expert Systems with Applications, Numero 292, 2025, ISSN 0957-4174
Editore: Elsevier BV
DOI: 10.1016/J.ESWA.2025.128596

Recent Advances in Automatic Term Extraction: A Comprehensive Survey

Autori: Hanh Thi Hong Tran, Matej Martinc, Jaya Caporusso, Julien Delaunay, Antoine Doucet, Senja Pollak
Pubblicato in: ACM Computing Surveys, Numero 58, 2026, ISSN 0360-0300
Editore: Association for Computing Machinery (ACM)
DOI: 10.1145/3787584

Računalniška analiza slovenskih zgodovinskih časopisov (1771–1914): jezikovni, tematski in državotvorni uvidi

Autori: Ajda Pretnar Žagar
Pubblicato in: Contributions to Contemporary History, Numero 65, 2025, ISSN 2463-7807
Editore: Institut za novejso zgodovino
DOI: 10.51663/PNZ.65.3.02

Retrieval-augmented code completion for local projects using large language models

Autori: Marko Hostnik, Marko Robnik-Šikonja
Pubblicato in: Expert Systems with Applications, Numero 292, 2025, ISSN 0957-4174
Editore: Elsevier BV
DOI: 10.1016/J.ESWA.2025.128596

Mono- and cross-lingual evaluation of representation language models on less-resourced languages

Autori: Matej Ulčar, Aleš Žagar, Carlos S. Armendariz, Andraž Repar, Senja Pollak, Matthew Purver, Marko Robnik-Šikonja
Pubblicato in: Computer Speech & Language, Numero 95, 2025, ISSN 0885-2308
Editore: Elsevier BV
DOI: 10.1016/J.CSL.2025.101852

Grammatical error correction of Slovenian school essays using large language models

Autori: Matej Klemen, Martin Božič, Špela Arhar Holdt, Marko Robnik-Šikonja
Pubblicato in: Sodobna pedagogika, Numero 76, 2025, ISSN 0038-0474
Editore: Zveza društev pedagoških delavcev Slovenije
DOI: 10.63384/SPTB53Z793A

Assessing Sentiments Towards Artificial Intelligence in the Croatian Media Using the ChatGPT Artificial Intelligence Tool

Autori: Ivana Erceg Matijašević, Martina Baričević Debelec, Ljerka Luić
Pubblicato in: Medijska istraživanja, Numero 30, 2024, ISSN 1846-6605
Editore: Media Research
DOI: 10.22572/MI.30.2.1

Other (2)

SyntaxFest 2025: 5 Events for 1 Fest of Empirical Syntax

Pubblicato in: 2025
Editore: Založba Univerze v Ljubljani (University of Ljubljana Press)
DOI: 10.4312/9789612976361

Cultural Memory from Antagonism to Deliberation in (Social) Media: AI Approach

Autori: Horvat, Marjan; Koražija, Jure; Babnik, Jan; Skvorc, Tadej; Robnik-Šikonja, Marko

Monographic books (1)

SyntaxFest 2025: 5 Events for 1 Fest of Empirical Syntax.

Autori: Dobrovoljc Kaja, Terčon Luka
Pubblicato in: 2025, ISBN 978-961-297-636-1
Editore: Založba Univerze v Ljubljani.
DOI: 10.4312/9789612976361