Open Source Contributions

Multilingual Passage Reranking Model

• It now has a high six-digit number of downloads
• It has been rated as one of the most efficient of its kind in various scientific papers:

• On cross-lingual retrieval with multilingual text encoders
• Improving NLP Model Performance on Small Educational Data Sets Using Self-Augmentation
• Query-Based Retrieval of German Regulatory Documents for Internal Auditing Purposes
• Better Retrieval May Not Lead to Better Question Answering
• Answer Similarity Grouping and Diversification in Question Answering Systems
• On cross-lingual retrieval with multilingual text encoders

High quality, German training data set

• High-quality data sets are required to train AI models and avoid certain biases.
• Together with Philipp May, T-Systems, we have defined this training dataset to train our LLMs.
• When we train AI models, we do not use customer data, but general, public data – such as from this training dataset.

German Electra Model

• Together with Philip May, T-Systems, we have published an improved Electra model, which was trained with 1.5 million steps.
• At the time of publication in August 2020, it was briefly the most efficient German-language LLM.
• Of course, it is now far from state of the art. But it shows how early we started working with large language models and that we have own expertise in this technology.