mlsanityData to 7 Oct 2026

Learning Passage Impacts for Inverted Indexes

arXiv 2104.12016 ↗First posted 24 Apr 2021cs.IRcited by 68

Not on the map. Why?

Abstract (arXiv)

Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized language models such as BERT. In this paper, we propose DeepImpact, a new document term-weighting scheme suitable for efficient retrieval using a standard inverted index. Compared to existing methods, DeepImpact improves impact-score modeling and tackles the vocabulary-mismatch problem. In particular, DeepImpact leverages DocT5Query to enrich the document collection and, using a contextualized language model, directly estimates the semantic importance of tokens in a document, producing a single-value representation for each token in each document. Our experiments show that DeepImpact significantly outperforms prior first-stage retrieval approaches by up to 17% on effectiveness metrics w.r.t. DocT5Query, and, when deployed in a re-ranking scenario, can reach the same effectiveness of state-of-the-art approaches with up to 5.1x speedup in efficiency.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Apr 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 18; 2023: 10; 2024: 10; 2025: 12; 2026: 11.

68 papers.

Sort:

By area:

  1. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  2. 2021SPLADE v2: Sparse Lexical and Expansion Model for Information Retrievalcited by 126
  3. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 112
  4. 2022From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effectivecited by 98
  5. 2022PLAID: An Efficient Engine for Late Interaction Retrievalcited by 95
  6. 2021A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniquescited by 69
  7. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 59
  8. 2022Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generationcited by 47
  9. 2024Scaling Laws For Dense Retrievalcited by 28
  10. 2022An Efficiency Study for SPLADE Modelscited by 26
  11. 2021A Proposed Conceptual Framework for a Representational Approach to Information Retrievalcited by 24
  12. 2022Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reductioncited by 21
38 more
  1. 2022In Defense of Cross-Encoders for Zero-Shot Retrievalcited by 21
  2. 2024Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challengescited by 20
  3. 2022CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrievalcited by 19
  4. 2025NExtLong: Toward Effective Long-Context Training without Long Documentscited by 19
  5. 2023Multiview Identifiers Enhanced Generative Retrievalcited by 16
  6. 2022LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrievalcited by 15
  7. 2023Constructing Tree-based Index for Efficient and Effective Dense Retrievalcited by 15
  8. 2024Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Modelcited by 15
  9. 2023Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answeringcited by 11
  10. 2025Efficient Constant-Space Multi-Vector Retrievalcited by 10
  11. 2025CSPLADE: Learned Sparse Retrieval with Causal Language Modelscited by 10
  12. 2022Query-as-context Pre-training for Dense Passage Retrievalcited by 9
  13. 2023DAPR: A Benchmark on Document-Aware Passage Retrievalcited by 9
  14. 2024Mistral-SPLADE: LLMs for better Learned Sparse Retrievalcited by 8
  15. 2025Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrievalcited by 8
  16. 2023ESPN: Memory-Efficient Multi-Vector Information Retrievalcited by 7
  17. 2023Exploring the Practicality of Generative Retrieval on Dynamic Corporacited by 6
  18. 2025Enhancing Lexicon-Based Text Embeddings with Large Language Modelscited by 6
  19. 2021Sparsifying Sparse Representations for Passage Retrieval by Top-k Maskingcited by 5
  20. 2026Learning Retrieval Models with Sparse Autoencoderscited by 5
  21. 2021CODER: An efficient framework for improving retrieval through COntextual Document Embedding Rerankingcited by 4
  22. 2022Learning Diverse Document Representations with Deep Query Interactions for Dense Retrievalcited by 4
  23. 2022Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrievalcited by 4
  24. 2022Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrievalcited by 4
  25. 2023Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrievalcited by 4
  26. 2024Self-Retrieval: End-to-End Information Retrieval with One Large Language Modelcited by 4
  27. 2024Measuring Bias in a Ranked List using Term-based Representationscited by 4
  28. 2025The Role of Vocabularies in Learning Sparse Representations for Rankingcited by 4
  29. 2023Adapting Learned Sparse Retrieval for Long Documentscited by 3
  30. 2024Measuring Retrieval Complexity in Question Answering Systemscited by 3
  31. 2024QAEncoder: Towards Aligned Representation Learning in Question Answering Systemscited by 3
  32. 2025An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doccited by 3
  33. 2025Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrievalcited by 3
  34. 2023NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoderscited by 2
  35. 2023SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrievalcited by 2
  36. 2026On the Challenges and Opportunities of Learned Sparse Retrieval for Codecited by 2
  37. 2022Query Expansion and Entity Weighting for Query Reformulation Retrieval in Voice Assistant Systemscited by 1
  38. 2022Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Rankingcited by 1

50 most cited of 68 All 68 (JSON)