About me

About me

About me

  • Currently working as a Solutions Engineer at Prefect & living in Berlin (Germany)
  • Before I was working as IT consultant, Data Engineer & Python Programmer in various industries (audit, aerospace, e-commerce, financial & energy trading sectors)
  • Technical writer with +500.000 views on Medium.
  • Goal: support companies in building reliable data ecosystems and sharing knowledge through my blog
  • AWS Certified Solution Architect, passionate about building scalable and sustainable solutions to complex business problems

My NLP research

Together with Prof. Roland Müller, we published in 2021: "Research Method Classification with Deep Transfer Learning for Semi-Automatic Meta-Analysis of Information Systems Papers"

Here are some interesting findings I got from that research:

  • Classification of large text documents is MUCH harder than classifying shorter texts such as tweets or emails - in this paper, we were trying to predict the correct categories by taking the entire documents as inputs. Long texts make it harder to a model to distinguish between signal and noise and learn useful feature representations.
  • Multilabel classification is much more challenging than a binary classification (such as ex. fraud or not, spam or not) because each text document can be assigned different categories. Plus, often datasets used for training such models are quite imbalanced (prevalence of one most common class).
  • Even though transfer learning significantly improves the learned representations, deep transfer learning (ex. ELMo, BERT, ULMFiT, OpenAI Transformer) allows to learn more context-dependent word representations which are much richer than shallow transfer learning techniques such as word2vec or GloVe.

If you work with lots of text data and are interested, have a look at the paper: https://scholarspace.manoa.hawaii.edu/handle/10125/71357