Hi there! I’m Jia-Huei (Dylan) Ju, currently pursuing my PhD at the University of Amsterdam. I work at the IRLab and am under the supervision of Dr. Andrew Yates since 2024. My research focuses on natural language processing and neural information retrieval.
Previously, I served as a full-time research assistant at the Research Center for IT Innovation at Academia Sinica, and was supervised by Prof. Chuan-Ju Wang. I completed my master’s degree in Management Information Systems from National Chengchi University, where I was advised by Professors Howard Hao-Chun Chuang and Yen-Chun Chou. During my master’s program, I specialized in econometric modeling and stochastic optimization.
My recent research interests revolve around representation learning and retrieval-augmented generation, encompassing:
- Retrieval-enhanced machine learning
- Enhanced information access
- Knowledge/context management for multi-stage RAG
- Retrieval-based language modeling via in-context learning
- Neural information retrieval (text)
- Out-of-domain dataset augmentation for weakly-supervised text retrieval
- Unsupervised representation learning for domain-specific retrieval approaches
- Specialized text ranking methods
- Instruction-followed retrieval approaches for knowledge-intensive tasks
- Passage re-ranking and candidate pruning
- Interactive (conversational) search
- End-to-end mixed-initiative response generation
- Personalized open-domain conversational question answering
Feel free to contact me via email: j.{lastname}[at]uva.nl. I’m open to inquiries and feedback related to my research interests and excited to explore potential research collaborations :)