New Data Spaces – SPP 2431

@inproceedings{Abusaleh:et:al:2026,
  title     = {Learning to Detect Cross-Modal Negation: An Analysis of Latent
               Representations and an Attention-Based Solution},
  author    = {Abusaleh, Ali and Hammerla, Leon and Mehler, Alexander},
  booktitle = {2026 8th International Conference on Natural Language Processing (ICNLP)},
  eventdate = {2026-03-20/2026-03-22},
  location  = {Xi'an,China},
  year      = {2026},
  keywords  = {Vision language model, Natural language processing, Cross-modal retrieval, negation detection, video analysis, Multimodal analysis, Political Communication, neglab, new-data-spaces, circlet},
  abstract  = {Detecting high-level semantic concepts like negation across modalities
               remains a challenge for current multimodal systems. We analyze
               this as a fundamental representation learning problem, providing
               the first evidence that negation does not form a linearly or non-linearly
               separable class in the latent spaces of standard vision-language
               models (VLMs). We demonstrate that pretrained embeddings primarily
               encode modality-specific features, lacking a generalizable negation
               signal. To overcome this, we propose a novel cross-modal attention
               architecture that explicitly models inter-modal dependencies,
               achieving performance gains of up to +7.03% F1 over unimodal baselines.
               Our analysis reveals a key asymmetry: while textual negation often
               appears independently, visual negation is semantically dependent
               on linguistic context, a finding validated through our statistical
               analysis of 3,222 political video-text pairs automatically annotated
               via Qwen2.5-VL. By combining this analysis with self-supervised
               video representations (JEPA2), we advance the modeling of temporal
               negation. This work provides new methods and insights for learning
               robust, semantically-aligned representations in multimodal systems.},
  note      = {accepted}
}

@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{Bundan:Abrami:Mehler:2025,
  author    = {Bundan, Daniel and Abrami, Giuseppe and Mehler, Alexander},
  title     = {Multimodal Docker Unified {UIMA} Interface: New Horizons for Distributed
               Microservice-Oriented Processing of Corpora using {UIMA}},
  booktitle = {Proceedings of the 21st Conference on Natural Language Processing
               (KONVENS 2025): Long and Short Papers},
  year      = {2025},
  editor    = {Wartena, Christian and Heid, Ulrich},
  location  = {Hildesheim, Germany},
  address   = {Hannover, Germany},
  publisher = {HsH Applied Academics},
  pages     = {257--268},
  series    = {KONVENS '25},
  url       = {https://aclanthology.org/2025.konvens-1.22/},
  pdf       = {https://aclanthology.org/2025.konvens-1.22.pdf},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2025/09/Poster_Multimodal_DUUI_KONVENS_2025.pdf},
  keywords  = {duui,neglab,new-data-spaces,circlet}
}

@inproceedings{Boenisch:et:al:2025,
  title     = {Towards Unified, Dynamic and Annotation-based Visualisations and
               Exploration of Annotated Big Data Corpora with the Help of Unified
               Corpus Explorer},
  author    = {B{\"o}nisch, Kevin and Abrami, Giuseppe and Mehler, Alexander},
  editor    = {Dziri, Nouha and Ren, Sean (Xiang) and Diao, Shizhe},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas
               Chapter of the Association for Computational Linguistics: Human
               Language Technologies (System Demonstrations)},
  year      = {2025},
  address   = {Albuquerque, New Mexico},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2025.naacl-demo.42/},
  pages     = {522--534},
  isbn      = {979-8-89176-191-9},
  abstract  = {The annotation and exploration of large text corpora, both automatic
               and manual, presents significant challenges across multiple disciplines,
               including linguistics, digital humanities, biology, and legal
               science. These challenges are exacerbated by the heterogeneity
               of processing methods, which complicates corpus visualization,
               interaction, and integration. To address these issues, we introduce
               the Unified Corpus Explorer (UCE), a standardized, dockerized,
               open-source and dynamic Natural Language Processing (NLP) application
               designed for flexible and scalable corpus navigation. Herein,
               UCE utilizes the UIMA format for NLP annotations as a standardized
               input, constructing interfaces and features around those annotations
               while dynamically adapting to the corpora and their extracted
               annotations. We evaluate UCE based on a user study and demonstrate
               its versatility as a corpus explorer based on generative AI.},
  note      = {Best Demo Award},
  pdf       = {https://aclanthology.org/2025.naacl-demo.42.pdf},
  keywords  = {uce,new-data-spaces,circlet,core,core_c08}
}

@article{Abrami:et:al:2025:a,
  title     = {Docker Unified UIMA Interface: New perspectives for NLP on big data},
  journal   = {SoftwareX},
  volume    = {29},
  pages     = {102033},
  year      = {2025},
  issn      = {2352-7110},
  doi       = {https://doi.org/10.1016/j.softx.2024.102033},
  url       = {https://www.sciencedirect.com/science/article/pii/S2352711024004047},
  author    = {Giuseppe Abrami and Markos Genios and Filip Fitzermann and Daniel Baumartz
               and Alexander Mehler},
  keywords  = {Docker, Kubernetes, UIMA, Distributed NLP, duui, biofid, neglab, new-data-spaces, circlet, core, core_c08},
  abstract  = {Processing large amounts of natural language text using machine
               learning-based models is becoming important in many disciplines.
               This demand is being met by a variety of approaches, resulting
               in the heterogeneous deployment of separate, partly incompatible,
               not natively scalable applications. To overcome the technological
               bottleneck involved, we have developed Docker Unified UIMA Interface,
               a system for the standardized, parallel, platform-independent,
               distributed and microservices-based solution for processing large
               and extensive text corpora with any NLP method. We present DUUI
               as a framework that enables automated orchestration of GPU-based
               NLP processes beyond the existing Docker Swarm cluster variant,
               and in addition to the adaptation to new runtime environments
               such as Kubernetes. Therefore, a new driver for DUUI is introduced,
               which enables the lightweight orchestration of DUUI processes
               within a Kubernetes environment in a scalable setup. In this way,
               the paper opens up novel text-technological perspectives for existing
               practices in disciplines that deal with the scientific analysis
               of large amounts of data based on NLP.}
}