Sparse neural retrieval finally started getting more and more attention (SPARSEUP, MILCO, sparse encoders in Sentence Transformers…). Well, amazing, we like attention!
Our miniCOIL v1 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.
source & further reading
qdrant.tech — original article
SHIFTing Languages in Multilingual RAG
Hyperbolic Embeddings in Qdrant
What to Check Before Tuning a Qdrant Collection