@inproceedings{bonisch-etal-2025-towards,
    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)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/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."
}