Matthias Aßenmacher

Contact

Department of Statistics, LMU Munich
Ludwigstraße 33, D-80539 München
matthias [at] stat [dot] uni [minus] muenchen [dot] de

Teaching

• Winter 2024/25
  • Deep Learning for NLP
  • Fundamentals of Statistics (for Economists)
• Summer 2024:
  • Statistics I & II for Economists
• Winter 2023/24
  • Deep Learning for NLP
  • Statistics I for Economists
• Summer 2023:
  • Statistics I & II for Economists
  • Introduction to Python
• Winter 2022/23
  • Deep Learning for NLP
  • Statistics I for Economists
• Summer 2022:
  • Statistics I & II for Economists
  • Seminar (Multimodal Deep Learning)
  • Introduction to Python
• Winter 2021/22:
  • Deep Learning for NLP
  • Statistics I & II for Economists
• Earlier courses, can be found here

Research Interests

My main research interest lies in Natural Language Processing, for more details see the NLP focus group page.

Thesis supervision

I supervise theses on various topics related to NLP. Please read the following information before writing me an e-mail:

• If you are interested in writing your thesis under my supervision, please include the following information in your e-mail
  • your field of interest and at least a tentative idea for the direction of a potential thesis topic
  • a CV, and your current transcript of records
  • a planned starting date for your thesis (you should also bring some time for developing and refining a research idea, so do not expect to start in e.g. one week)
• Disclaimer: Before you apply for a thesis topic regarding NLP make sure that you fit the following profile:
  • Willingness and ability to engage in a topic which (potentially) requires a notable amount of self-study, since it is normally not part of the regular curriculum of your studies in statistics.
  • Readiness to do quite some programming (most probably in Python)
  • Please include the following information in the email mentioned above: Previously experience/attended classes on NLP, deep learning, machine learning, and programming.
  • This is not meant to discourage you from writing your thesis on NLP, but rather to get expectations straight in advance.
• If you want to apply for supervision of an external thesis, please also include the following information in your email:
  • A clear formulation of the thesis goal from an academic perspective of ~1 page (It should not be a pure business case, such projects are better suited for e.g. the Consulting module)
  • Information on the external partner, data availability (detailed please), computational resources supplied by the project partner (if applicable)
  • Again: Not meant to discourage you or to set any artificial barriers, but to get expectations/goals straight in advance.

A selection of theses I recently supervised (partly together with Christian Heumann) can be found here.

You Can Find me on

• Google Scholar
• GitHub
• HuggingFace
• ORCID
• LinkedIn

References

1. Deiseroth B, Meuer M, Gritsch N, Eichenberg C, Schramowski P, Aßenmacher M, Kersting K (2024) Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization. Accepted at NAACL 2024.
   link|pdf.
2. Gruber C, Hechinger K, Aßenmacher M, Kauermann G, Plank B (2024) More Labels or Cases? Assessing Label Variation in Natural Language Inference Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language, pp. 22–32. Association for Computational Linguistics, Malta.
   link|pdf.
3. Garces Arias E, Pai V, Schöffel M, Heumann C, Aßenmacher M (2023) Automatic Transcription of Handwritten Old Occitan Language Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 15416–15439. Association for Computational Linguistics, Singapore.
   link|pdf.
4. Schulze P, Wiegrebe S, Thurner PW, Heumann C, Aßenmacher M, Wankmüller S (2023) Exploring Topic-Metadata Relationships with the STM: A Bayesian Approach. Accepted at Advances in Statistical Analysis (AStA).
   link.
5. Koch P, Nuñez GV, Garces Arias E, Heumann C, Schöffel M, Häberlin A, Aßenmacher M (2023) A tailored Handwritten-Text-Recognition System for Medieval Latin First Workshop on Ancient Language Processing (ALP 2023),
   link|pdf.
6. Aßenmacher M, Sauter N, Heumann C (2023) Classifying multilingual party manifestos: Domain transfer across country, time, and genre. arXiv preprint arXiv:2307.16511.
   link|pdf.
7. Aßenmacher M, Rauch L, Goschenhofer J, Stephan A, Bischl B, Roth B, Sick B (2023) Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering Proceedings of the 7th Workshop on Interactive Adaptive Learning (co-located with ECML-PKDD 2023),
   link|pdf.
8. Urchs S, Thurner V, Aßenmacher M, Heumann C, Thiemichen S (2023) How Prevalent is Gender Bias in ChatGPT? - Exploring German and English ChatGPT Responses 1st Workshop on Biased Data in Conversational Agents (co-located with ECML-PKDD 2023),
   link|pdf.
9. Öztürk IT, Nedelchev R, Heumann C, Garces Arias E, Roger M, Bischl B, Aßenmacher M (2023) How Different Is Stereotypical Bias Across Languages? 3rd Workshop on Bias and Fairness in AI (co-located with ECML-PKDD 2023),
   link|pdf.
10. Rauch L, Aßenmacher M, Huseljic D, Wirth M, Bischl B, Sick B (2023) ActiveGLAE: A Benchmark for Deep Active Learning with Transformers ECML-PKDD 2023,
    link|pdf.
11. Witte M, Schwenzow J, Heitmann M, Reisenbichler M, Aßenmacher M (2023) Potential for Decision Aids based on Natural Language Processing Proceedings of the European Marketing Academy, 52nd, (114322),
    link|pdf.
12. Vogel M, Aßenmacher M, Gubler A, Attin T, Schmidlin PR (2023) Cleaning potential of interdental brushes around orthodontic brackets-an in vitro investigation. Swiss Dental Journal 133.
    link|pdf.
13. Akkus C, Chu L, Djakovic V, Jauch-Walser S, Koch P, Loss G, Marquardt C, Moldovan M, Sauter N, Schneider M, Schulte R, Urbanczyk K, Goschenhofer J, Heumann C, Hvingelby R, Schalk D, Aßenmacher M (2023) Multimodal Deep Learning. arXiv preprint arXiv:2301.04856.
    link|pdf.
14. Goschenhofer J, Ragupathy P, Heumann C, Bischl B, Aßenmacher M (2022) CC-Top: Constrained Clustering for Dynamic Topic Discovery Proceedings of the The First Workshop on Ever Evolving NLP (EvoNLP), pp. 26–34. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Hybrid).
    link|pdf.
15. Lebmeier E, Aßenmacher M, Heumann C (2022) On the current state of reproducibility and reporting of uncertainty for Aspect-based Sentiment Analysis Machine Learning and Knowledge Discovery in Databases (ECML-PKDD), Springer International Publishing, Grenoble, France.
    link|pdf.
16. Aßenmacher M, Dietrich M, Elmaklizi A, Hemauer EM, Wagenknecht N (2022) Whitepaper: New Tools for Old Problems.
    link.
17. Koch P, Aßenmacher M, Heumann C (2022) Pre-trained language models evaluating themselves - A comparative study Proceedings of the Third Workshop on Insights from Negative Results in NLP, pp. 180–187. Association for Computational Linguistics, Dublin, Ireland.
    link|pdf.
18. Aßenmacher M, Schulze P, Heumann C (2021) Benchmarking down-scaled (not so large) pre-trained language models Proceedings of the 17th Conference on Natural Language Processing (KONVENS 2021), pp. 14–27. KONVENS 2021 Organizers, Düsseldorf, Germany.
    link|pdf.
19. Aßenmacher M, Corvonato A, Heumann C (2021) Re-Evaluating GermEval17 Using German Pre-Trained Language Models Proceedings of the Swiss Text Analytics Conference 2021, CEUR Workshop Proceedings, Winterthur, Switzerland (Online).
    link|pdf.
20. Schulze P, Wiegrebe S, Thurner PW, Heumann C, Aßenmacher M, Wankmüller S (2021) Exploring Topic-Metadata Relationships with the STM: A Bayesian Approach. arXiv preprint arXiv:2104.02496.
    link|pdf.
21. Lebmeier E, Hou N, Spann K, Aßenmacher M (2021) Creating a Customer Centricity Graph from unstructured customer feedback. Applied Marketing Analytics 6, 221–229.
    link|pdf.
22. Meidinger M, Aßenmacher M (2021) A New Benchmark for NLP in Social Sciences: Evaluating the Usefulness of Pre-trained Language Models for Classifying Open-ended Survey Responses Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, pp. 866–873. SciTePress.
    link|pdf.
23. Schiergens TS, Drefs M, Dörsch M, Kühn F, Albertsmeier M, Niess H, Schoenberg MB, Assenmacher M, Küchenhoff H, Thasler WE, others (2021) Prognostic Impact of Pedicle Clamping during Liver Resection for Colorectal Metastases. Cancers 13, 72.
    link|pdf.
24. Guderlei M, Aßenmacher M (2020) Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News Proceedings of the 28th International Conference on Computational Linguistics, pp. 6339–6349. International Committee on Computational Linguistics, Barcelona, Spain (Online).
    link|pdf.
25. Viellieber VD, Aßenmacher M (2020) Pre-trained language models as knowledge bases for Automotive Complaint Analysis. arXiv preprint arXiv:2012.02558.
    link|pdf.
26. Aßenmacher M, Heumann C (2020) On the comparability of pre-trained language models Proceedings of the 5th Swiss Text Analytics Conference and 16th Conference on Natural Language Processing, CEUR Workshop Proceedings, Zurich, Switzerland (Online).
    link|pdf.
27. Aßenmacher M, Kaiser JC, Zaballa I, Gasparrini A, Küchenhoff H (2019) Exposure-lag-response associations between lung cancer mortality and radon exposure in German uranium miners. Radiation and Environmental Biophysics.
    link|pdf.
28. Sint A, Lutz R, Assenmacher M, Küchenhoff H, Kühn F, Faist E, Bazhin AV, Rentsch M, Werner J, Schiergens TS (2019) Monocytic HLA-DR expression for prediction of anastomotic leak after colorectal surgery. Journal of the American College of Surgeons 229, 200–209.
    link.
29. Deffner V, Kreuzer M, Sobotzki C, Aßenmacher M, Güthlin D, Kaiser C, Küchenhoff H, Fenske N (2019) Uncertainties in radiation exposure assessment in the Wismut cohort: a preliminary evaluation BIO Web of Conferences, p. 03009. EDP Sciences.
    link|pdf.
30. Küchenhoff H, Deffner V, Aßenmacher M, Neppl H, Kaiser C, Güthlin D, others (2018) Ermittlung der Unsicherheiten der Strahlenexpositionsabschätzung in der Wismut-Kohorte-Teil I-Vorhaben 3616S12223.
    link|pdf.
31. Brandl C, Breinlich V, Stark KJ, Enzinger S, Aßenmacher M, Olden M, Grassmann F, Graw J, Heier M, Peters A, others (2016) Features of age-related macular degeneration in the general adults and their dependency on age, sex, and smoking: results from the German KORA study. PloS one 11, e0167181.
    link|pdf.