Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever

Rohan Jha, Bo Wang, Michael Günther, Saba Sturua, Mohammad Kalim Akram, Han Xiao

Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever: 10 upvotes on Hugging Face Daily Papers, #13 of 16 papers on 2024-09-02. Day-by-day upvote history.

Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this paper, we introduce several improvements to the ColBERT model architecture and training pipeline, leveraging techniques successful in the more established single-vector embedding model paradigm, particularly those suited for heterogeneous multilingual data. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks, while also cutting storage requirements by up to 50% compared to previous models.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.