# miniCOIL EN-ES: Sparse Neural Retrieval Across the Language Barrier

> Source: <https://qdrant.tech/articles/minicoil-en-es/>
> Published: 2026-10-08 07:00:00+00:00

*Sparse neural retrieval finally started getting more and more attention ([SPARSEUP](https://www.linkup.so/blog/introducing-sparseup-by-linkup), [MILCO](https://arxiv.org/abs/2510.00671), [sparse encoders in Sentence Transformers](https://huggingface.co/blog/train-sparse-encoder)…). Well, amazing, we like attention!*

Our [miniCOIL v1](https://qdrant.tech/articles/minicoil/) sparse neural retriever article ended with a promise: to keep working on this sparse neural retriever in-depth, improving the model’s quality, and in-width, *“extending it to other dense encoders and to languages beyond English.”*

Here is the next “in-width” step of the miniCOIL saga: to try and cross the language barrier, that is, make the model suitable for multilingual retrieval.

It’s a fun challenge, as sparse retrievers are hard to adapt to this scenario: exact matching in cross-lingual text search usually means translation.