MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch
This work addresses a gap for Dutch language processing by providing new evaluation and modeling resources, though it is incremental as it adapts existing methods to a specific language.
The paper tackles the underrepresentation of Dutch in embedding resources by introducing MTEB-NL, a benchmark for evaluating Dutch embeddings, and E5-NL, efficient embedding models, achieving strong performance across multiple tasks.
Recently, embedding resources, including models, benchmarks, and datasets, have been widely released to support a variety of languages. However, the Dutch language remains underrepresented, typically comprising only a small fraction of the published multilingual resources. To address this gap and encourage the further development of Dutch embeddings, we introduce new resources for their evaluation and generation. First, we introduce the Massive Text Embedding Benchmark for Dutch (MTEB-NL), which includes both existing Dutch datasets and newly created ones, covering a wide range of tasks. Second, we provide a training dataset compiled from available Dutch retrieval datasets, complemented with synthetic data generated by large language models to expand task coverage beyond retrieval. Finally, we release a series of E5-NL models compact yet efficient embedding models that demonstrate strong performance across multiple tasks. We make our resources publicly available through the Hugging Face Hub and the MTEB package.