Pith. sign in

REVIEW 2 cited by

Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.06918 v3 pith:DORALZQJ submitted 2021-10-13 cs.CL cs.IRcs.LG

Xilun Chen , Kushal Lakhotia , Barlas Oğuz , Anchit Gupta , Patrick Lewis , Stan Peshterliev , Yashar Mehdad , Sonal Gupta
show 1 more author
Wen-tau Yih
This is my paper · ORCID
classification cs.CLcs.IRcs.LG
keywords densesparsparseretrieversalientawareimitatelambda
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data. It has been argued that this is an inherent limitation of dense models. We rebut this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. We show that a dense Lexical Model {\Lambda} can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with {\Lambda}. Empirically, SPAR shows superior performance on a range of tasks including five question answering datasets, MS MARCO passage retrieval, as well as the EntityQuestions and BEIR benchmarks for out-of-domain evaluation, exceeding the performance of state-of-the-art dense and sparse retrievers. The code and models of SPAR are available at: https://github.com/facebookresearch/dpr-scale/tree/main/spar

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs

    cs.IR 2025-01 conditional novelty 6.0 of 10

    A citation-graph retrieval framework that entangles sparse and dense relevance signals in a GNN over paper chunks reports state-of-the-art Hit@1 and answer accuracy on two research QA benchmarks.

  2. Remining Hard Negatives for Generative Pseudo Labeled Domain Adaptation

    cs.IR 2025-01 conditional novelty 5.0 of 10

    Periodically refreshing hard negatives with the in-training retriever improves unsupervised domain adaptation of dense retrievers over the static GPL baseline.

Pith tools