Supervision

Supervised Theses

• Kai Pons “Evaluating Different Kinds of Model Architectures for Natural Language Understanding in Conversational Agents”, 2019. Bielefed University, MSc
• Aya Ahmaro “Building Natural Language to SQL Systems (NL2SQL) Using Sequence-to-Sequence Models”, 2019. Bielefed University, MSc
• Hoang Kiet Ta “Detection of Scientific Claims in Videos from Social Media”, 2021, Leibniz University Hannover, MSc
• Hussain Kanafani “Evaluating and Extending Unsupervised Video Summarization Methods”, 2021, Leibniz University Hannover, MSc

Open Topics

** Fine-tuning Large Language Models on Specific Domains: This project involves using existing code bases to fine-tune LlaMa model on various new domains. The required skills to have would be previous experience in training machine learning models, familiarity with following instructions from another Github repository and being able to install/run the code. The access to GPUs will be provided by the group for training.

Required skills: Python, Familiarity with any Deep Learning library (Pytorch, Tensorflow), Natural Language Processing, Computer Vision