4th Workshop on Digital Humanities and Natural Language Processing

13-16 avril 2026, Salvador, Bahia (Brésil)

Date : 13-16 avril 2026
Lieu : Salvador, Bahia, Brésil
Site internet : lien
Date de soumission : 19 février 2026
Notification aux auteurs : 12 mars 2026

Modalités de soumission :

– Short papers consisting of up to 4 pages of content, plus unlimited pages of references (in English or Portuguese)
– Long papers consisting of up to 8 pages of content, plus unlimited pages of references (in English or Portuguese)
All papers must be anonymous, original and not simultaneously submitted to another journal or conference. They must strictly adhere to the submission templates of the main conference (below).

Mises en forme des soumission :

– LaTeX styelesheet: https://github.com/acl-org/acl-style-files/archive/refs/heads/master.zip
– Overleaf template: https://www.overleaf.com/latex/templates/association-for-computational-linguistics-acl-conference/jvxskxpnznfj
– Paper formatting guidelines: https://acl-org.github.io/ACLPUB/formatting.html

CMT submission link: https://cmt3.research.microsoft.com/PROPOR2026/Track/8/Submission/Create

Comité d’Organisation :

Leonardo Zilio – Université catholique de Louvain, CENTAL, LSTI , Belgium
Helena Freire Cameron – Instituto Politécnico de Portalegre, CIDEHUS, Évora, Portugal
Maria José Bocorny Finatto – Universidade Federal do Rio Grande do Sul, PPG-LETRAS, Brazil
Renata Vieira – Universidade de Évora, CIDEHUS, Portugal

Argumentaire :

Digital humanities (DH) stand at the intersection of computing and the humanities, involving collaborative transdisciplinary research. While current DH practice already shows an impressive array of new digital tools and methods for the study of the humanities, we believe that natural language processing techniques and experience can significantly enhance the field, while DH can also bring new testbeds and problems for the NLP community.

The 4th DHanNLP workshop, co-located with PROPOR, brings together researchers of both research traditions (humanities and computational linguists), with interests in multi- and cross-lingual approaches, and also those with interests in Portuguese language variants and dialects (including the language varieties of Portugal, Brazil, Cape Verde, Guinea-Bissau, Mozambique, Angola, São Tomé, Macau or Galiza). We expect papers stemming from humanities that deal with language, such as philosophy, history, geography, law, philology, linguistics, or literature, and that can benefit from a digital approach or enhanced with computational linguistics methods or techniques, be it by using large sets of (written or spoken) textual data or by developing applications for an increasingly digital world. Also expected are papers that describe and evaluate the use of well-known techniques in new DH applications.

List of non-exclusive, indicative areas of interest for the DHandNLP workshop:
– Lexical distribution and computational text analysis
– Lexicometrics, lexicology and lexicography
– Textual and discourse complexity studies
– Keywords and terminology extraction
– Construction of historical thesauri and glossaries
– Historical lexicography and lexicology
– Historical and diachronic corpora processing
– Digital paleography
– Digital philology, critical editions production and textual criticism
– Multilingual analysis of diachronic/historical corpora
– Use and construction of ontologies
– Linked data
– Document clustering and classification
– Topic modelling
– Word sense disambiguation
– Information Extraction
– Named entity recognition
– Sentiment analysis
– Cross-lingual NLP methods
– Pronunciation / sonic patterns
– Visualization or sonification of large textual bodies in specific domains
– Corpus visualization
– Computational stylometry, authorship attribution and profiling
– Distant reading of literature
– Multimodal approaches to DH (e.g., combining text, speech, image analysis)
– Resources and encoding of digital collections
– Analysis and recognition of language variants and dialects