Betty started working at the DATEXIS team as a Research Assistant in 2018.
She graduated with a Master's degree in Media Informatics from the Beuth University of Applied Sciences in Berlin in 2017. During and after her studies she used to work as a Software Engineer. One of her focuses and the research topic of her master's thesis was the development of chatbot applications.
At DATEXIS Betty worked on the project NOHATE, funded by the Federal Ministry of Education and Research. The project aims included to develop solutions for the detection of Hatespeech in online discussions with the help of Deep Learning techniques.
Betty's current research focuses on NLP for the medical domain. Specifically she wants to find out how to use patient information in clinical notes to improve decision support systems for medical professionals. In this regard, she wants to build explainable systems that leverage publicly available medical data.
- Deep Learning
- NLP for the medical domain
- VisBERT - How Does BERT Answer Questions?
- Clinical Outcome Prediction Demo
- Assertion Detection in Clinical Notes
- NOHATE Demo
- NOHATEbot - Telegram Chatbot for Labeling of German User Comments
- Outcome Prediction from Clinical Notes at Admission Time - Future Medicine Science Pitch, Tagesspiegel
- An Evening with BERT - PyLadies Berlin
- Betty van Aken, Ivana Trajanovska, Amy Siu, Manuel Mayrdorfer, Klemens Budde, Alexander Loeser. Assertion Detection in Clinical Notes: Medical Language Models to the Rescue? Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations (NLPMC@NAACL'21) [PDF] [Data]
- Betty van Aken, Jens-Michalis Papaioannou, Manuel Mayrdorfer, Klemens Budde, Felix Gers, Alexander Löser. Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration. The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL'21) [PDF] [Code]
- Betty van Aken, Benjamin Winter, Felix A. Gers and Alexander Löser. VisBERT: Hidden-State Visualizations for Transformers. The Web Conference 2020 (WWW'20) Demo Track [PDF] [Code]
- Sebastian Arnold, Betty van Aken, Paul Grundmann, Felix A. Gers and Alexander Löser. Learning Contextualized Document Representations for Healthcare Answer Retrieval. The Web Conference 2020 (WWW'20) [PDF] [Code]
- Betty van Aken, Benjamin Winter, Felix A. Gers and Alexander Löser. How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations. The 28th ACM International Conference on Information and Knowledge Management (CIKM'19) [PDF] [Code]
- Betty van Aken, Julian Risch, Ralf Krestel, Alexander Löser. Challenges for Toxic Comment Classification: An In-Depth Error Analysis 2nd Workshop on Abusive Language Online (ALW@EMNLP'18) [PDF]
Advised Bachelor- / Mastertheses
- Ivana Trajanovska, Assertion Detection in Electronic Health Records, Master Thesis, Beuth University of Applied Sciences, 2020
- Sebastian Jäger, Compressing BERT - An Evaluation and Combination of Methods, Master Thesis, Beuth University of Applied Sciences, 2020
- Arndt Allhorn, Transfer Learning for Hate Speech Detection, Master Thesis, Beuth University of Applied Sciences, 2020
- Sebastian Herrmann, Generating Electronic Health Records: an Investigation on Gender-Medicine and Rare Diseases, Bachelor Thesis, Beuth University of Applied Sciences, 2020.
- TheWebConf 2021 Research Track
- NAACL 2021
- TheWebConf 2020 Research Track
- AAAI 2020
- EMNLP 2019
- NAACL 2019 Industry Track
- TheWebConf 2019 Research Track
- Workshop on Abusive Language Online @ ACL 2019