The 5th International Conference on Natural Language Processing for Digital Humanities – NLP4DH 2025

The 5th International Conference on Natural Language Processing for Digital Humanities (NLP4DH 2025) will be organized together with NAACL 2025. The proceedings of the conference will be published in the ACL anthology. The conference will take place in Albuquerque, USA on May 3–4, 2025.

Main Track

The focus of the conference is on applying natural language processing techniques to digital humanities research. The topics can be anything of digital humanities interest with a natural language processing or generation aspect. 

A list of suitable topics includes but is not limited to:

• Text analysis and processing related to humanities using computational methods

• Thorough error analysis of an NLP system using (digital) humanities methods

• Dataset creation and curation for NLP (e.g. digitization, digitalization, datafication, and data preservation).

• Research on cultural heritage collections such as national archives and libraries using NLP

• NLP for error detection, correction, normalization and denoising data

• Generation and analysis of literary works such as poetry and novels

• Analysis and detection of text genres

Special Track: Understanding LLMs through humanities

As we established in the previous edition of NLP4DH, humanities research has a new role in interpreting and explaining the behavior of LLMs. Reporting numerical results on some benchmarks is not quite enough, we need humanities research to better understand LLMs. This line of research is emerging and we know that it may take several shapes and forms. Here is some list of examples of what this could mean.

• Using theories to analyze or qualitatively evaluate LLMs

• Using insights from humanities to improve LLMs

• Using theories to probe LLMs

• Examining LLMs through linguistic typology and variation

• The influence of literary theories on understanding LLM-generated text

• Philosophical inquiries into the "understanding" of language in LLMs

• Analyzing LLM responses using narratology frameworks

• Cognitive models of human language acquisition vs. LLM training paradigms

Schedule - Room: Taos

Program committee

Hale Sirin, Johns Hopkins University

Thibault Clérice, INRIA Paris - Almanach

Noémi Ligeti-Nagy, Hungarian Research Centre for Linguistics

Anna Dmitrieva, University of Helsinki

Frederik Arnold, Humboldt Universität Berlin

Dongqi Liu, Universität des Saarlandes

Won Ik Cho, Samsung Advanced Institute of Technology

Konstantin Schulz, Humboldt Universität Berlin

Aynat Rubinstein, Hebrew University of Jerusalem

Alejandro Sierra Múnera, Hasso Plattner Institute

Tim Fischer, University of Hamburg

Shu Okabe, Technische Universität München

Ronja Laarmann-Quante, Ruhr-Universtät Bochum

Yoshifumi Kawasaki, The University of Tokyo

Klara Venglarova, Universität Graz

Youngsook Song, Sionic AI

Joshua Wilbur, University of Tartu

Keito Inoshita, Shiga University

Kenichi Iwatsuki, Mirai Translate

Piper Vasicek, Brigham Young University

Mohammed Attia, Google

Laura Manrique-Gómez, Universidad de Los Andes

Craig Messner, Johns Hopkins University

Abhai Pratap Singh, Carnegie Mellon University

Balázs Indig, Eötvös Lorand University

Anton Eklund, Umeå University

Jouni Tuominen, University of Helsinki

Jesse Roberts, Tennessee Technological University

Nikita Neveditsin, St. Mary's University

William Thorne, University of Sheffield

Lev Kharlashkin, Metropolia University of Applied Sciences

Jonne Sälevä, Brandeis University

Gleb Schmidt, Radboud University

Erik Henriksson, University of Turku

Amanda Myntti, University of Turku

Erkki Mervaala, University of Helsinki

Jay Park, Nanyang Technological University

Lama Alqazlan, University of Warwick

Pascale Moreira, Aarhus University

Enrique Manjavacas, Arevalo University of Leiden

Chahan Vidal-Gorène, École Nationale des Chartes

Lucija Krusic, Karl-Franzens-Universität Graz

Lidia Pivovarova, University of Helsinki

Iana Atanassova, University of Franche-Comté

Sebastian Oliver Eck, University of Oxford

Shuo Zhang, Bose Corporation

Tomasz Walkowiak, Wroclaw University of Science and Technology

Elissa Nakajima, Wickham Waseda University

Nicolas Gutehrlé, University Bourgogne Franche-Comté

Hanna-Mari Kupari, University of Turku

Sourav Das, Indian Institute of Information Technology Kalyani

Antti Kanner, University of Helsinki

Julie-Anne Meaney, University of Edinburgh

Eetu Mäkelä, University of Helsinki

Fotini Koidaki, University of Crete

Yuzuki Tsukagoshi, University of Tokyo

Quanqi Du, Ghent University

Hugo Gonçalo Oliveira, Universidade de Coimbra

Maciej Kurzynski, Lingnan University

Xinmeng Hou, Columbia University

Sijia Ge, University of Colorado at Boulder

Mary Ogbuka Kenneth, Imperial College London

Mina Rajaei Moghadam, Northern Illinois University

Quan Duong, University of Helsinki

Mohamed Hannani, Universität Siegen

Pascale Feldkamp, Aarhus University

Eiaki Morooka, Metropolia University of Applied Sciences

Jahnavi Anilkumar Kachhia, Facebook

Rynaa Grover, Google

Milavkumar Sha, IEEE

Pratik Aher, Meta

Kunal Chhabaria, Walmart Connect

Elena Klyachko, HSE University

Yulia Badryzlova, Higher School of Economics

Mariia Fedorova, University of Oslo