Publications

Automated Extraction of Fine-Grained Standardized Product Information from Unstructured Multilingual Web Data
We implement models that reliably predict product attributes across online shops, languages, or both, and can be used to match product taxonomies between online retailers.
PDF Project DOI
GreenDB - A Dataset and Benchmark for Extraction of Sustainability Information of Consumer Goods
We present a second public release of the GreenDB and present a first benchmark for sustainability information extraction.
PDF Code Dataset Slides DOI
Nudging Sustainable Consumption: A Large-Scale Data Analysis of Sustainability Labels for Fashion in German Online Retail
A Large-Scale data analysis of sustainability labels for fashion in German online retail.
PDF DOI
GreenDB: Toward a Product-by-Product Sustainability Database
We present the first public release of the GreenDB and describe its scraping pipeline.
PDF Code Dataset DOI
A Benchmark for Data Imputation Methods
Comparison of data imputation methods on a wide range of datasets, missingness patterns, and missingness fractions.
PDF Code DOI
Compressing BERT - An Evaluation and Combination of Methods
Evaluation and improvement of BERT-of-Theseus based on real world datasets and tasks.
PDF
Parallelized Training of Deep NN – Comparison of Current Concepts and Frameworks
Kubernetes based evaluation of TensorFlows’ and MXNet’s throughput, scalability and practical ease of use.
Slides DOI
Machine Learning Im Kubernetes Cluster
Erläutert wie Kubernetes und das passenden Tooling hilft, Machine-Learning-Projekte effizient und erfolgreich umzusetzen.
Source Document
Horizontales Skalieren Von Deep Learning Frameworks
Kubernetes basierte Evaluation der horizontalen Skalierbarkeit von TensorFlow und MXNet mit Hilfe der Datensätze Fashion-MNIST und PTB.
PDF