@inproceedings{KohlFreyerKraemeretal.2023,
  author    = {Kohl, Philipp and Freyer, Nils and Kr{\"a}mer, Yoka and Werth, Henri and Wolf, Steffen and Kraft, Bodo and Meinecke, Matthias and Z{\"u}ndorf, Albert},
  title     = {ALE: a simulation-based active learning evaluation framework for the parameter-driven comparison of query strategies for NLP},
  series = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science},
  booktitle = {Deep Learning Theory and Applications. DeLTA 2023. Communications in Computer and Information Science},
  editor    = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-031-39058-6 (Print)},
  doi       = {978-3-031-39059-3},
  pages     = {235 -- 253},
  year      = {2023},
  abstract  = {Supervised machine learning and deep learning require a large amount of labeled data, which data scientists obtain in a manual, and time-consuming annotation process. To mitigate this challenge, Active Learning (AL) proposes promising data points to annotators they annotate next instead of a subsequent or random sample. This method is supposed to save annotation effort while maintaining model performance. However, practitioners face many AL strategies for different tasks and need an empirical basis to choose between them. Surveys categorize AL strategies into taxonomies without performance indications. Presentations of novel AL strategies compare the performance to a small subset of strategies. Our contribution addresses the empirical basis by introducing a reproducible active learning evaluation (ALE) framework for the comparative evaluation of AL strategies in NLP. The framework allows the implementation of AL strategies with low effort and a fair data-driven comparison through defining and tracking experiment parameters (e.g., initial dataset size, number of data points per query step, and the budget). ALE helps practitioners to make more informed decisions, and researchers can focus on developing new, effective AL strategies and deriving best practices for specific use cases. With best practices, practitioners can lower their annotation costs. We present a case study to illustrate how to use the framework.},
  language  = {en}
}
@inproceedings{KloeserBuesgenKohletal.2023,
  author    = {Kl{\"o}ser, Lars and B{\"u}sgen, Andr{\´e} and Kohl, Philipp and Kraft, Bodo and Z{\"u}ndorf, Albert},
  title     = {Explaining relation classification models with semantic extents},
  series = {DeLTA 2023: Deep Learning Theory and Applications},
  booktitle = {DeLTA 2023: Deep Learning Theory and Applications},
  editor    = {Conte, Donatello and Fred, Ana and Gusikhin, Oleg and Sansone, Carlo},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-031-39058-6 (Print)},
  doi       = {10.1007/978-3-031-39059-3_13},
  pages     = {189 -- 208},
  year      = {2023},
  abstract  = {In recent years, the development of large pretrained language models, such as BERT and GPT, significantly improved information extraction systems on various tasks, including relation classification. State-of-the-art systems are highly accurate on scientific benchmarks. A lack of explainability is currently a complicating factor in many real-world applications. Comprehensible systems are necessary to prevent biased, counterintuitive, or harmful decisions. We introduce semantic extents, a concept to analyze decision patterns for the relation classification task. Semantic extents are the most influential parts of texts concerning classification decisions. Our definition allows similar procedures to determine semantic extents for humans and models. We provide an annotation tool and a software framework to determine semantic extents for humans and models conveniently and reproducibly. Comparing both reveals that models tend to learn shortcut patterns from data. These patterns are hard to detect with current interpretability methods, such as input reductions. Our approach can help detect and eliminate spurious decision patterns during model development. Semantic extents can increase the reliability and security of natural language processing systems. Semantic extents are an essential step in enabling applications in critical areas like healthcare or finance. Moreover, our work opens new research directions for developing methods to explain deep learning models.},
  language  = {en}
}