Publication

@article{Borkowski:et:al:2026,
  title     = {{DUUIgateway}: A Web Service for Platform-independent, Ubiquitous Big Data NLP},
  journal   = {SoftwareX},
  volume    = {34},
  pages     = {102549},
  year      = {2026},
  issn      = {2352-7110},
  doi       = {https://doi.org/10.1016/j.softx.2026.102549},
  url       = {https://www.sciencedirect.com/science/article/pii/S2352711026000439},
  author    = {Borkowski, Cedric and Abrami, Giuseppe and Terefe, Dawit and Baumartz, Daniel
               and Mehler, Alexander},
  keywords  = {duui, neglab, core, core_b05, core_c08, new-data-spaces, circlet},
  abstract  = {Distributed processing of unstructured text data is a challenge
               in the rapidly changing and evolving natural language processing
               (NLP) landscape. This landscape is characterized by heterogeneous
               systems, models, and formats, and especially by the increasing
               influence of AI systems. While many of these systems handle text
               data, there are also unified systems that process multiple input
               and output formats, while allowing for distributed corpus processing.
               However, there are hardly any user-friendly interfaces that allow
               existing NLP frameworks to be used flexibly and extended in a
               user-controlled manner. Due to this gap and the increasing importance
               of NLP for various scientific disciplines, there has been a demand
               for a web and API based flexible software solution for deploying,
               managing and monitoring NLP systems. Such a solution is provided
               by Docker Unified UIMA-gateway. We introduce DUUIgateway and evaluate
               its API and user-driven approach to encapsulation. We also describe
               how these features improve the usability and accessibility of
               the NLP framework DUUI. We illustrate DUUIgateway in the field
               of process modeling in higher education and show how it closes
               the latter gap in NLP by making a variety of systems for processing
               text and multimodal data accessible to non-experts.}
}

@inproceedings{Hammerla:et:al:2025a,
  author    = {Hammerla, Leon and Mehler, Alexander and Abrami, Giuseppe},
  title     = {Standardizing Heterogeneous Corpora with {DUUR}: A Dual Data-
               and Process-Oriented Approach to Enhancing NLP Pipeline Integration},
  editor    = {Inui, Kentaro and Sakti, Sakriani and Wang, Haofen and Wong, Derek F.
               and Bhattacharyya, Pushpak and Banerjee, Biplab and Ekbal, Asif and Chakraborty, Tanmoy
               and Singh, Dhirendra Pratap},
  booktitle = {Proceedings of the 14th International Joint Conference on Natural
               Language Processing and the 4th Conference of the Asia-Pacific
               Chapter of the Association for Computational Linguistics},
  month     = {dec},
  year      = {2025},
  address   = {Mumbai, India},
  publisher = {The Asian Federation of Natural Language Processing and The Association for Computational Linguistics},
  url       = {https://aclanthology.org/2025.findings-ijcnlp.87/},
  pages     = {1410--1425},
  isbn      = {979-8-89176-303-6},
  abstract  = {Despite their success, LLMs are too computationally expensive
               to replace task- or domain-specific NLP systems. However, the
               variety of corpus formats makes reusing these systems difficult.
               This underscores the importance of maintaining an interoperable
               NLP landscape. We address this challenge by pursuing two objectives:
               standardizing corpus formats and enabling massively parallel corpus
               processing. We present a unified conversion framework embedded
               in a massively parallel, microservice-based, programming language-independent
               NLP architecture designed for modularity and extensibility. It
               allows for the integration of external NLP conversion tools and
               supports the addition of new components that meet basic compatibility
               requirements. To evaluate our dual data- and process-oriented
               approach to standardization, we (1) benchmark its efficiency in
               terms of processing speed and memory usage, (2) demonstrate the
               benefits of standardized corpus formats for NLP downstream tasks,
               and (3) illustrate the advantages of incorporating custom formats
               into a corpus format ecosystem.},
  keywords  = {neglab,duui}
}

@inproceedings{Hammerla:et:al:2025b,
  author    = {Hammerla, Leon and Lücking, Andy and Reinert, Carolin and Mehler, Alexander},
  title     = {{D}-Neg: Syntax-Aware Graph Reasoning for Negation Detection},
  editor    = {Inui, Kentaro and Sakti, Sakriani and Wang, Haofen and Wong, Derek F.
               and Bhattacharyya, Pushpak and Banerjee, Biplab and Ekbal, Asif and Chakraborty, Tanmoy
               and Singh, Dhirendra Pratap},
  booktitle = {Proceedings of the 14th International Joint Conference on Natural
               Language Processing and the 4th Conference of the Asia-Pacific
               Chapter of the Association for Computational Linguistics},
  month     = {dec},
  year      = {2025},
  address   = {Mumbai, India},
  publisher = {The Asian Federation of Natural Language Processing and The Association for Computational Linguistics},
  url       = {https://aclanthology.org/2025.findings-ijcnlp.89/},
  pages     = {1432--1454},
  isbn      = {979-8-89176-303-6},
  abstract  = {Despite the communicative importance of negation, its detection
               remains challenging. Previous approaches perform poorly in out-of-domain
               scenarios, and progress outside of English has been slow due to
               a lack of resources and robust models. To address this gap, we
               present D-Neg: a syntax-aware graph reasoning model based on a
               transformer that incorporates syntactic embeddings by attention-gating.
               D-Neg uses graph attention to represent syntactic structures,
               emulating the effectiveness of rule-based dependency approaches
               for negation detection. We train D-Neg using 7 English resources
               and their translations into 10 languages, all aligned at the annotation
               level. We conduct an evaluation of all these datasets in in-domain
               and out-of-domain settings. Our work represents a significant
               advance in negation detection, enabling more effective cross-lingual
               research.},
  keywords  = {neglab}
}

@inproceedings{Christof:et:al:2025,
  author    = {Christof, Roman and Zeidi, Farnaz and Messelhäußer, Manuela and Mentzer, Dirk
               and Koenig, Renate and Childs, Liam and Mehler, Alexander},
  title     = {{M}ed{L}ink{DE} {--} {M}ed{DRA} Entity Linking for {G}erman with
               Guided Chain of Thought Reasoning},
  editor    = {Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn
               and Peng, Violet},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural
               Language Processing},
  month     = {nov},
  year      = {2025},
  address   = {Suzhou, China},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2025.emnlp-main.1609/},
  doi       = {10.18653/v1/2025.emnlp-main.1609},
  pages     = {31569--31581},
  isbn      = {979-8-89176-332-6},
  pdf       = {https://aclanthology.org/2025.emnlp-main.1609.pdf},
  abstract  = {In pharmacovigilance, effective automation of medical data structuring,
               especially linking entities to standardized terminologies such
               as MedDRA, is critical. This challenge is rarely addressed for
               German data. With MedLinkDE we address German MedDRA entity linking
               for adverse drug reactions in a two-step approach: (1) retrieval
               of medical terms with fine-tuned embedding models, followed (2)
               by guided chain-of-thought re-ranking using LLMs. To this end,
               we introduce RENOde, a German real-world MedDRA dataset consisting
               of reportings from patients and healthcare professionals. To overcome
               the challenges posed by the linguistic diversity of these reports,
               we generate synthetic data mapping the two reporting styles of
               patients and healthcare professionals. Our embedding models, fine-tuned
               on these synthetic, quasi-personalized datasets, show competitive
               performance with real datasets in terms of accuracy at high top-
               recall, providing a robust basis for re-ranking. Our subsequent
               guided Chain of Thought (CoT) re-ranking, informed by MedDRA coding
               guidelines, improves entity linking accuracy by approximately
               15{\%} (Acc@1) compared to embedding-only strategies. In this
               way, our approach demonstrates the feasibility of entity linking
               in medical reports under the constraints of data scarcity by relying
               on synthetic data reflecting different informant roles of reporting
               persons.}
}