English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper introduces Sparsified Late Interaction for Multi-vector (SLIM)retrieval with inverted indexes. Multi-vector retrieval methods havedemonstrated their effectiveness on various retrieval datasets, and among them,ColBERT is the most established method based on the late interaction ofcontextualized token embeddings of pre-trained language models. However,efficient ColBERT implementations require complex engineering and cannot takeadvantage of off-the-shelf search libraries, impeding their practical use. Toaddress this issue, SLIM first maps each contextualized token vector to asparse, high-dimensional lexical space before performing late interactionbetween these sparse token embeddings. We then introduce an efficient two-stageretrieval architecture that includes inverted index retrieval followed by ascore refinement module to approximate the sparsified late interaction, whichis fully compatible with off-the-shelf lexical search libraries such as Lucene.SLIM achieves competitive accuracy on MS MARCO Passages and BEIR compared toColBERT while being much smaller and faster on CPUs. To our knowledge, we arethe first to explore using sparse token representations for multi-vectorretrieval. Source code and data are integrated into the Pyserini IR toolkit.

SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes