@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}
}
@article{SildatkeKarwanniKraftetal.2023,
  author    = {Sildatke, Michael and Karwanni, Hendrik and Kraft, Bodo and Z{\"u}ndorf, Albert},
  title     = {A distributed microservice architecture pattern for the automated generation of information extraction pipelines},
  series = {SN Computer Science},
  journal   = {SN Computer Science},
  number    = {4, Article number: 833},
  publisher = {Springer Singapore},
  address   = {Singapore},
  issn      = {2661-8907},
  doi       = {10.1007/s42979-023-02256-4},
  pages     = {19 Seiten},
  year      = {2023},
  abstract  = {Companies often build their businesses based on product information and therefore try to automate the process of information extraction (IE). Since the information source is usually heterogeneous and non-standardized, classic extract, transform, load techniques reach their limits. Hence, companies must implement the newest findings from research to tackle the challenges of process automation. They require a flexible and robust system that is extendable and ensures the optimal processing of the different document types. This paper provides a distributed microservice architecture pattern that enables the automated generation of IE pipelines. Since their optimal design is individual for each input document, the system ensures the ad-hoc generation of pipelines depending on specific document characteristics at runtime. Furthermore, it introduces the automated quality determination of each available pipeline and controls the integration of new microservices based on their impact on the business value. The introduced system enables fast prototyping of the newest approaches from research and supports companies in automating their IE processes. Based on the automated quality determination, it ensures that the generated pipelines always meet defined business requirements when they come into productive use.},
  language  = {en}
}