Performance of Dense Retrievers on Synthetic Typo-Injected Dutch Data vs. English Baselines in BEIR-NL Benchmark

Zero-shot evaluation of information retrieval (IR) models is often performed using BEIR; a large and heterogeneous benchmark composed of multiple datasets, covering different retrieval tasks across various domains. Although BEIR has become a standard benchmark for the zero-shot setup, its exclusively English content reduces its utility for underrepresented languages in IR, including Dutch. To address this limitation and encourage the development of Dutch IR models, we introduce BEIR-NL by automatically translating the publicly accessible BEIR datasets into Dutch. Using BEIR-NL, we evaluated a

Research goal: How does the performance of dense retrievers trained on synthetic typo-injected Dutch data compare to English baselines on the BEIR-NL benchmark across low-resource domains?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.5/10.