@inproceedings{SchmidtsKraftWinkensetal.2020,
  author    = {Schmidts, Oliver and Kraft, Bodo and Winkens, Marvin and Z{\"u}ndorf, Albert},
  title     = {Catalog integration of low-quality product data by attribute label ranking},
  series = {Proceedings of the 9th International Conference on Data Science, Technology and Applications DATA - Volume 1},
  booktitle = {Proceedings of the 9th International Conference on Data Science, Technology and Applications DATA - Volume 1},
  publisher = {SciTePress},
  address   = {Set{\´u}bal, Portugal},
  isbn      = {978-989-758-440-4},
  doi       = {10.5220/0009831000900101},
  pages     = {90 -- 101},
  year      = {2020},
  abstract  = {The integration of product data from heterogeneous sources and manufacturers into a single catalog is often still a laborious, manual task. Especially small- and medium-sized enterprises face the challenge of timely integrating the data their business relies on to have an up-to-date product catalog, due to format specifications, low quality of data and the requirement of expert knowledge. Additionally, modern approaches to simplify catalog integration demand experience in machine learning, word vectorization, or semantic similarity that such enterprises do not have. Furthermore, most approaches struggle with low-quality data. We propose Attribute Label Ranking (ALR), an easy to understand and simple to adapt learning approach. ALR leverages a model trained on real-world integration data to identify the best possible schema mapping of previously unknown, proprietary, tabular format into a standardized catalog schema. Our approach predicts multiple labels for every attribute of an inpu t column. The whole column is taken into consideration to rank among these labels. We evaluate ALR regarding the correctness of predictions and compare the results on real-world data to state-of-the-art approaches. Additionally, we report findings during experiments and limitations of our approach.},
  language  = {en}
}
@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}
}