Back to top

Joshua Oehms

Last modified Mar 5
   No tags assigned
School of Computation, Information and Technology
Department of Computer Science, I19
Software Engineering for
Business Information Systems (sebis)    
 
Technical University of Munich
Boltzmannstraße 3
85748 Garching, Germany
 
joshua.oehms[at]tum.de
Room FMI: 01.12.038 
Office hours: by appointment

Curriculum Vitae

Joshua Oehms joined sebis in July 2024. He holds an B.Sc. and M.Sc. in Games Engineering from the Technical University of Munich. In his master studies he focused on NLP tasks and developed a special interest in text simplification.

Research Interests

  • Information Retrieval
  • Conversational Systems
  • NLP for Healthcare Applications
  • Low resource NLP

 

Open Thesis Topics

Master Thesis: Reducing Manual Effort in Medical Literature Screening (In Collaboration with MRI)

To produce high-quality systematic reviews, medical researchers need to populate and maintain dedicated databases including thousands of medical publications regarding their specialist area. Medical databases such as PubMed are searched at regular intervals to identify relevant new publications based on title/abstract and add them to their own specialized database. This process is currently carried out manually and consumes rare financial and temporal resources. We therefore want to examine approaches to automation based on a specific specialist area. As this topic is highly relevant to the field, it is very likely that a Master's thesis will result in a publication.

Helpful skills:

- motivation for interdisciplinary research

- Pytorch/Keras/similar

- experience with transformer models and their training

- experience with traditional Information Retrieval

If you are interested, please apply by email with your CV, your grade transcript and a short statement of why you are interessted and your related skills. 

Please use as subject line: MRI-Thesis-Application.

Teaching

 

Term     Level Title Type Role
WS 24/25 Bachelor Software Engineering for Business Applications - Bachelor's Course (SEBA Bachelor) Lecture Organizer

 

Publications

2023 Miriam Anschütz, Joshua Oehms, Thomas Wimmer, BartÅ‚omiej Jezierski, and Georg Groh. 2023. Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training. In Findings of the Association for Computational Linguistics: ACL 2023