Koustav Rudra
Assistant Professor
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (10)
Year:
2026
Year:
2025
Year:
2025
Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even for fine-tuning. In this article, we propose data-augmentation methods for effective and robust ranking performance. One of the key benefits of using data augmentation is in achieving sample efficiency or learning effectively when we have only a small amount of training data. We propose supervised and unsupervised data augmentation schemes by creating training data using parts of the relevant documents in the query-document pairs. We then adapt a family of contrastive losses for the document ranking task that can exploit the augmented data to learn an effective ranking model. Our extensive experiments on subsets of the MS MARCO and TREC-DL test sets show that data augmentation, along with the ranking-adapted contrastive losses, results in performance improvements under most dataset sizes. Apart from sample efficiency, we conclusively show that data augmentation results in robust models when transferred to out-of-domain benchmarks. Our performance improvements in in-domain and more prominently in out-of-domain benchmarks show that augmentation regularizes the ranking model and improves its robustness and generalization capability.
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2023
Year:
2023
Collaborators (5)
Avishek Anand
Associate Professor
Delft University of Technology
Eric Müller-Budack
Group Leader
-
Marco Fisichella
Leibniz University Hannover
Wolfgang Nejdl
Leibniz University Hannover
Ritumbra Manuvie
Scientific Staff, Assistant Professor, Universitair docent
University of Groningen
Make your next move.
Prepare your application
Review drafts before you send them.