From the Makers of Haystack: Ask your Data with Neural Search (in German too!)

The next meeting of the Data Science @ Regensburg – meetup group will highlight an area that combines natural language processing and search – automatic Question-Answering. In the last few years plenty of new advances have been made in this area, but primarily for languages such as English. But recently a German QA data set was published.

This data set comes from deepset from Berlin. At the meetup, Branden Chan, NLP Engineer at deepset, and Timo Möller, Co-founder and Head of Machine Learning at deepset, will present their new data set.


Search is ubiquitous. It’s expected to be packaged with just about any program that interacts with text. With breakthroughs in Machine Learning (ML) and Natural Language Processing (NLP), search technology has taken a big leap forward and we at deepset are committed to tracking the latest trends. Our open source framework, Haystack, is a collection of NLP pipelines which can sift through millions of documents, answer full sentence questions and summarize documents. With the release of our new German Question Answering and Passage Retrieval datasets (, Neural Search is now also available in the German language. In this talk, we will be discussing what is possible today in the realm of Neural Search, and offer first hand advice about how to make it work for your language and your domain.

Wednesday, 06-09-2021, 07.00 p.m. – 09.00 p.m., virtual event

More details & registration at:

This is an event of the Data Science @ Regensburg – Meetup group.