Lesson plan
Learned sparse retrieval
Learned sparse retrieval (LSR) or sparse neural search is an approach to Information Retrieval which uses a sparse vector representation of queries and documents. It borrows techniques both from lexical bag-of-words and vector embedding algorithms, and is claimed to perform better than either alone. The best-known sparse neural search systems are SPLADE and its successor SPLADE v2. Others include DeepCT, uniCOIL, EPIC, DeepImpact, TILDE and TILDEv2, Sparta, SPLADE-max, and DistilSPLADE-max. Multimodal Learned Sparse Retrieval. LSR approaches have also been extended to the vision-language domain, where they are applied to multimodal data, such as the combination of text and images. This expansion enables the retrieval of relevant content across different modalities, such as finding images based on text queries or vice versa. Some implementations of SPLADE have similar latency to Okapi BM25 lexical search while giving as good results as state-of-the-art neural rankers on in-domain data. The Official SPLADE model weights and training code is released under a Creative Commons NonCommercial license. But there are other independent implementations of SPLADE++ (a variant of SPLADE models) that are released under permissive licenses. SPRINT is a toolkit for evaluating neural sparse retrieval systems.
Article summary
Learned sparse retrieval (LSR) or sparse neural search is an approach to Information Retrieval which uses a sparse vector representation of queries and documents. It borrows techniques both from lexical bag-of-words and vector embedding algorithms, and is claimed to perform better than either alone. The best-known sparse neural search systems are SPLADE and its successor SPLADE v2. Others include DeepCT, uniCOIL, EPIC, DeepImpact, TILDE and TILDEv2, Sparta, SPLADE-max, and DistilSPLADE-max. Multimodal Learned Sparse Retrieval. LSR approaches have also been extended to the vision-language domain, where they are applied to multimodal data, such as the combination of text and images. This expansion enables the retrieval of relevant content across different modalities, such as finding images based on text queries or vice versa. Some implementations of SPLADE have similar latency to Okapi BM25 lexical search while giving as good results as state-of-the-art neural rankers on in-domain data. The Official SPLADE model weights and training code is released under a Creative Commons NonCommercial license. But there are other independent implementations of SPLADE++ (a variant of SPLADE models) that are released under permissive licenses. SPRINT is a toolkit for evaluating neural sparse retrieval systems.
Key claims
No claims recorded.
Discussion questions
- Summarise the article in your own words. Which single claim would you verify first, and why?
- Which claim in this article is most likely to be revised as the sources update? How would you check its current status?
- If two sources disagreed about one of these facts, what would you need in order to trust one over the other?
Bibliography
No sources recorded.
Key claims and bibliography are generated from the same tracked claims and sources as the article page.