@inproceedings{SchmidtsKraftWinkensetal.2021,
  author    = {Schmidts, Oliver and Kraft, Bodo and Winkens, Marvin and Z{\"u}ndorf, Albert},
  title     = {Catalog integration of heterogeneous and volatile product data},
  series = {DATA 2020: Data Management Technologies and Applications},
  booktitle = {DATA 2020: Data Management Technologies and Applications},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-83013-7},
  doi       = {10.1007/978-3-030-83014-4_7},
  pages     = {134 -- 153},
  year      = {2021},
  abstract  = {The integration of frequently changing, volatile product data from different manufacturers into a single catalog is a significant challenge for small and medium-sized e-commerce companies. They rely on timely integrating product data to present them aggregated in an online shop without knowing format specifications, concept understanding of manufacturers, and data quality. Furthermore, format, concepts, and data quality may change at any time. Consequently, integrating product catalogs into a single standardized catalog is often a laborious manual task. Current strategies to streamline or automate catalog integration use techniques based on machine learning, word vectorization, or semantic similarity. However, most approaches struggle with low-quality or real-world data. We propose Attribute Label Ranking (ALR) as a recommendation engine to simplify the integration process of previously unknown, proprietary tabular format into a standardized catalog for practitioners. We evaluate ALR by focusing on the impact of different neural network architectures, language features, and semantic similarity. Additionally, we consider metrics for industrial application and present the impact of ALR in production and its limitations.},
  language  = {en}
}
@inproceedings{KohlSchmidtsKloeseretal.2021,
  author    = {Kohl, Philipp and Schmidts, Oliver and Kl{\"o}ser, Lars and Werth, Henri and Kraft, Bodo and Z{\"u}ndorf, Albert},
  title     = {STAMP 4 NLP - an agile framework for rapid quality-driven NLP applications development},
  series = {Quality of Information and Communications Technology. QUATIC 2021},
  booktitle = {Quality of Information and Communications Technology. QUATIC 2021},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-85346-4},
  doi       = {10.1007/978-3-030-85347-1_12},
  pages     = {156 -- 166},
  year      = {2021},
  abstract  = {The progress in natural language processing (NLP) research over the last years, offers novel business opportunities for companies, as automated user interaction or improved data analysis. Building sophisticated NLP applications requires dealing with modern machine learning (ML) technologies, which impedes enterprises from establishing successful NLP projects. Our experience in applied NLP research projects shows that the continuous integration of research prototypes in production-like environments with quality assurance builds trust in the software and shows convenience and usefulness regarding the business goal. We introduce STAMP 4 NLP as an iterative and incremental process model for developing NLP applications. With STAMP 4 NLP, we merge software engineering principles with best practices from data science. Instantiating our process model allows efficiently creating prototypes by utilizing templates, conventions, and implementations, enabling developers and data scientists to focus on the business goals. Due to our iterative-incremental approach, businesses can deploy an enhanced version of the prototype to their software environment after every iteration, maximizing potential business value and trust early and avoiding the cost of successful yet never deployed experiments.},
  language  = {en}
}