Papers › DeeperImpact: Optimizing Sparse Learned Index Structures

DeeperImpact: Optimizing Sparse Learned Index Structures

27 May 2024arXiv:2405.17093archive 2025-07-28

Soyuj Basnet, Jerry Gou, Antonio Mallia, Torsten Suel

A lot of recent work has focused on sparse learned indexes that use deep neural architectures to significantly improve retrieval quality while keeping the efficiency benefits of the inverted index. While such sparse learned structures achieve effectiveness far beyond those of traditional inverted index-based rankers, there is still a gap in effectiveness to the best dense retrievers, or even to sparse methods that leverage more expensive optimizations such as query expansion and query term weighting. We focus on narrowing this gap by revisiting and optimizing DeepImpact, a sparse retrieval approach that uses DocT5Query for document expansion followed by a BERT language model to learn impact scores for document terms. We first reinvestigate the expansion process and find that the recently proposed Doc2Query -- query filtration does not enhance retrieval quality when used with DeepImpact. Instead, substituting T5 with a fine-tuned Llama 2 model for query prediction results in a considerable improvement. Subsequently, we study training strategies that have proven effective for other models, in particular the use of hard negatives, distillation, and pre-trained CoCondenser model initialization. Our results substantially narrow the effectiveness gap with the most effective versions of SPLADE.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

basnetsoyuj/improving-learned-index officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdafactorAdamAttentionAttention DropoutBERTBPEDense ConnectionsDropoutFocusGated Linear UnitInverse Square Root ScheduleLLaMALayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5Weight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections