Projects

Probing Large Pre-trained Multilingual Language Models for Typological Signals Master’s Thesis supervised by Prof. Shane Steinert-Threlkeld

• Conducted an in-depth analysis of large pre-trained multilingual language models to probe typological signals, aiming to uncover language-specific features and patterns across diverse languages
• Developed and implemented a comprehensive probing methodology, including novel linguistic tasks and evaluation metrics, to investigate the capabilities of multilingual language models in capturing typological properties Ontology-Based

Recommender System for E-Commerce Independent Study supervised by Prof. Christoph Eick

• Designed and implemented an ontology-based recommender system for an e-commerce website, leveraging Graph Neural Networks (GNNs) to enhance the accuracy of product recommendations
• Constructed a comprehensive ontology that captured domain-specific knowledge and relationships between products, enabling an understanding of user preferences and item characteristics
• Employed GNNs to model and learn complex interactions within the product ontology, achieving a accuracy rate of 72% in generating personalized recommendations for users, thereby improving customer engagement

---

Page Design