AAU NLP Aalborg University · Copenhagen

Publications

Research across our faculty.

A curated view of research across AAU NLP's faculty programmes and their connections.

The collection draws on ACL Anthology and official proceedings and publisher records. It includes work predating AAU appointments; for the complete institutional record, use AAU's research portal ↗.

80 publications

EMNLP 2026Conference paper2026

Few-shot Semantic Recovery Attacks on Image Embeddings

Yiyi Chen, Qiongkai Xu, and Johannes Bjerva

Introduces a few-shot black-box method for recovering captions and sensitive attributes from image embeddings, and tests the utility cost of current defences.

  • Security, Privacy & Safety
ACL 2026Conference paper2026

How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP

Kushal Tatariya, Artur Kulmizev, Wessel Poelman, Esther Ploeger, Marcel Bollmann, Johannes Bjerva, Jiaming Luo, Heather Lent, and Miryam de Lhoneux

Audits all non-English Wikipedia editions and shows why data quality—not language coverage alone—must be a first-class concern in multilingual NLP.

  • Multilingual & Lower-Resource NLP
  • Factuality, Reliability & Evaluation
Transactions of the ACLJournal article2025

NLP Security and Ethics, in the Wild

Heather Lent, Erick Galinkin, Yiyi Chen, Jens Myrup Pedersen, Leon Derczynski, and Johannes Bjerva

Audits ethical practice in NLP security and develops concrete guidance for harm minimisation and responsible disclosure.

  • Security, Privacy & Safety
  • Communities, Domains & Consequences
ACL 2025 · Short PapersConference paper2025

Limited-Resource Adapters Are Regularizers, Not Linguists

Marcell Fekete, Nathaniel Romney Robinson, Ernests Lavrinovics, Djeride Jean-Baptiste, Raj Dabre, Johannes Bjerva, and Heather Lent

  • Multilingual & Lower-Resource NLP
  • Factuality, Reliability & Evaluation
Transactions of the ACLJournal article2024

CreoleVal: Multilingual Multitask Benchmarks for Creoles

Heather Lent, Kushal Tatariya, Raj Dabre, Yiyi Chen, Marcell Fekete, Esther Ploeger, Li Zhou, Ruth-Ann Armstrong, Abee Eijansantos, Catriona Malau, Hans Erik Heje, Ernests Lavrinovics, Diptesh Kanojia, Paul Belony, Marcel Bollmann, Loïc Grobol, Miryam de Lhoneux, Daniel Hershcovich, Michel DeGraff, Anders Søgaard, and Johannes Bjerva

  • Multilingual & Lower-Resource NLP
  • Communities, Domains & Consequences
Transactions on Graph Data and KnowledgeJournal article2023

Knowledge Graph Embeddings: Open Challenges and Opportunities

Russa Biswas, Lucie-Aimée Kaffee, Michael Cochez, Stefania Dumbrava, Theis E. Jendal, Matteo Lissandrini, Vanessa Lopez, Eneldo Loza Mencía, Heiko Paulheim, Harald Sack, Edlira Kalemi Vakaj, and Gerard de Melo

  • Knowledge, Evidence & Reasoning
  • Factuality, Reliability & Evaluation
Transactions on Graph Data and KnowledgeJournal article2023

Large Language Models and Knowledge Graphs: Opportunities and Challenges

Jeff Z. Pan, Simon Razniewski, Jan-Christoph Kalo, Sneha Singhania, Jiaoyan Chen, Stefan Dietze, Hajira Jabeen, Janna Omeliyanenko, Wen Zhang, Matteo Lissandrini, Russa Biswas, Gerard de Melo, Angela Bonifati, Edlira Vakaj, Mauro Dragoni, and Damien Graux

  • Knowledge, Evidence & Reasoning
  • Factuality, Reliability & Evaluation
LREC 2022Conference paper2022

What a Creole Wants, What a Creole Needs

Heather Lent, Kelechi Ogueji, Miryam de Lhoneux, Orevaoghene Ahia, and Anders Søgaard

  • Multilingual & Lower-Resource NLP
  • Communities, Domains & Consequences
ACL 2022Conference paper2022

Challenges and Strategies in Cross-Cultural NLP

Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, and Anders Søgaard

  • Multilingual & Lower-Resource NLP
  • Communities, Domains & Consequences
CoNLL 2021Conference paper2021

On Language Models for Creoles

Heather Lent, Emanuele Bugliarello, Miryam de Lhoneux, Chen Qiu, and Anders Søgaard

  • Multilingual & Lower-Resource NLP
  • Language, Meaning & Typology

Scope

What is included here?

We include the peer-reviewed 2024–26 work identified in a faculty-wide audit, together with selected earlier landmarks that make each research trajectory legible. Canonical links point to ACL Anthology, official proceedings, or publisher records.

Preprints are omitted when no peer-reviewed version exists, and duplicate arXiv versions are suppressed. The crawl was last reconciled in September 2026; accuracy takes priority over a superficially exhaustive list.