David Stap

PhD Candidate, University of Amsterdam, Language Technology Lab

• E-mail: d.stap[at]uva[dot]com
• Address: Office L6.03, Science Park 900 (LAB42), 1012WX, Amsterdam
• Twitter
• Linkedin
• Google Scholar
• Github

Hi! I am David. I am a PhD candidate in the Language Technology Lab at the University of Amsterdam. I'm happy to be supervised by Christof Monz and Vlad Niculae. I obtained my BSc and MSc in Artificial Intelligence from the University of Amsterdam. I was intern at Amazon Research in Berlin with their awesome machine translation team, and earlier at Infosys in Bangalore.

My research focuses on understanding and improving multilingual machine translation. I'm interested in low-resource languages, and methods to improve performance for these languages.

Publications

• The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities. David Stap, Eva Hasler, Bill Byrne, Christof Monz and Ke Tran. ACL 2024.
  
• How Far Can 100 Samples Go? Unlocking Overall Zero-Shot Multilingual Translation via Tiny Multi-Parallel Data. Di Wu, Shaomu Tan, Yan Meng, David Stap and Christof Monz. Findings of ACL 2024.
    • PDF
• Multilingual k-Nearest-Neighbor Machine Translation. David Stap and Christof Monz. EMNLP 2023.
    • PDF
• Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens. David Stap, Vlad Niculae and Christof Monz. Findings of EMNLP 2023.
    • PDF
• Improving Domain Robustness in Neural Machine Translation with Fused Topic Knowledge Embeddings. Danai Xezonaki, Talaat Khalil, David Stap and Brandon James Denis. MT Summit 2023.
  
• UvA-MT's Participation in the WMT 2023 General Translation Shared Task. Di Wu, Shaomu Tan, David Stap, Ali Araabi, Christof Monz. EMNLP (WMT) 2023.
    • PDF
• ChatGPT is not a good indigenous translator. David Stap and Ali Araabi. ACL (AmericasNLP) 2023.
    • PDF
• Towards a General Purpose Machine Translation System for Sranantongo. Just Zwennicker and David Stap. EMNLP (WiNLP) 2022.
    • PDF
• Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks. Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Atharva Naik, Arjun Ashok, Arut Selvan Dhanasekaran, Anjana Arunkumar, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Virendrabhai Purohit, Ishani Mondal, Jacob William Anderson, Kirby C. Kuznia, Krima Doshi, Kuntal Kumar Pal, Maitreya Patel, Mehrad Moradshahi, Mihir Parmar, Mirali Purohit, Neeraj Varshney, Phani Rohitha Kaza, Pulkit Verma, Ravsehaj Singh Puri, rushang karia, Savan Doshi, Shailaja Keyur Sampat, Siddhartha Mishra, Sujan Reddy A, Sumanta Patro, Tanay Dixit, Xudong Shen, Chitta Baral, Yejin Choi, Noah A. Smith, Hannaneh Hajishirzi and Daniel Khashabi. EMNLP 2022.
    • PDF
• Conditional Image Generation and Manipulation for User-Specified Content. David Stap, Maurits Bleeker, Sarah Ibrahimi and Maartje ter Hoeve. CVPR (AICCW) 2020.
    • PDF • Video
• Gamification for learning by modelling in interactive learning environments. David Stap, Bert Bredeweg and Natasa Brouwer. BNAIC 2017.
    • PDF

Teaching

Student Supervision

• 2022 - Danai Xezonaki, MSc thesis Artificial Intelligence, UvA
• 2022 - Just Zwennicker, MSc thesis Data Science, UvA
• 2021 - Lysa Ngouateu & Xing Yu Pan, BSc thesis Artificial Intelligence, UvA
• 2021 - Ard Snijders, MSc thesis Data Science, UvA
• 2020 - Claartje Barkhof, MSc thesis Artificial Intelligence, UvA
• 2020 - Jeffrey Ng, MSc thesis Data Science, UvA

For supervision requests, please get in touch.

Teaching Assistant

• 2021 - Deep Learning for Natural Language Processing, MSc Artificial Intelligence, UvA
• 2020 - Deep Learning for Natural Language Processing, MSc Artificial Intelligence, UvA
• 2017 - Computational Logic, BSc Artificial Intelligence, UvA