Hello There !

Hi, I’m Martin, a researcher in the field of natural language processing at the German Research Institute for Artificial Intelligence (DFKI), in the Speech and Language Technology research group located in Berlin. I work on large language models. Previously, I was a machine learning engineer in the retail industry. I graduated in 2021 from the Conservatoire National des Arts et Métiers in Paris with an engineering degree in Computer Science Modelization and Optimization.

Research Interest

I study the inner workings of deep learning models, I am trying to answer questions like “What’s attention ?” and hopefully improve model efficiency. I am interrested in all things machine learning and their applications to natural language processing:

• Probabilistic Modeling
• Energy-Based Models
• Natural Language Processing
• Information Retrieval

Publications

Under review:

1. Courtois, M., Ostendorff, M., Hennig, L., & Rehm, G. Symmetric Dot-Product Attention for Efficient Training of BERT Language Models OpenReview

In chronological order:

1. Courtois, M., Filiot, A., & Ficheur, G. Distribution-Based Similarity Measures Applied to Laboratory Results Matching. In Applying the FAIR Principles to Accelerate Health Research in Europe in the Post COVID-19 Era (pp. 94-98). IOS Press (2021). PubMed

Education

• MSc in Computer Science Modelization and Optimization, 2018-2021 - CNAM Paris
• BSc in Computer Science, 2016-2018 - CNAM Paris