mlsanityData to 7 Oct 2026

Complementing Lexical Retrieval with Semantic Residual Embedding

arXiv 2004.13969 ↗First posted 29 Apr 2020cs.IRcited by 27

Not on the map. Why?

Abstract (arXiv)

This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model. CLEAR explicitly trains the neural embedding to encode language structures and semantics that lexical retrieval fails to capture with a novel residual-based embedding learning method. Empirical evaluations demonstrate the advantages of CLEAR over state-of-the-art retrieval models, and that it can substantially improve the end-to-end accuracy and efficiency of reranking pipelines.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 7; 2023: 5; 2024: 2; 2025: 3.

27 papers.

Sort:

By area:

  1. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  2. 2021Mr. TyDi: A Multi-lingual Benchmark for Dense Retrievalcited by 118
  3. 2021The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Modelscited by 81
  4. 2021A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniquescited by 69
  5. 2022Fine-Grained Distillation for Long Document Retrievalcited by 29
  6. 2021Extreme Multi-label Learning for Semantic Matching in Product Searchcited by 28
  7. 2021A Proposed Conceptual Framework for a Representational Approach to Information Retrievalcited by 24
  8. 2022CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typoscited by 22
  9. 2021Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claimscited by 16
  10. 2023Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboardcited by 15
  11. 2022SeDR: Segment Representation Learning for Long Documents Dense Retrievalcited by 6
  12. 2022Long-tailed Extreme Multi-label Text Classification with Generated Pseudo Label Descriptionscited by 5
15 more
  1. 2023Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrievalcited by 4
  2. 2025Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoningcited by 4
  3. 2021PGT: Pseudo Relevance Feedback Using a Graph-Based Transformercited by 3
  4. 2023Divide & Conquer for Entailment-aware Multi-hop Evidence Retrievalcited by 3
  5. 2025T2-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generationcited by 3
  6. 2022Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during Trainingcited by 2
  7. 2022Hybrid Inverted Index Is a Robust Accelerator for Dense Retrievalcited by 2
  8. 2025EncouRAGe: Evaluating RAG Local, Fast, and Reliablecited by 2
  9. 2021Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independencecited by 1
  10. 2022Multifaceted Improvements for Conversational Open-Domain Question Answeringcited by 1
  11. 2023EHI: End-to-end Learning of Hierarchical Index for Efficient Dense Retrievalcited by 1
  12. 2021Transferring Semantic Knowledge Into Language Encoderscited by 0
  13. 2023Hybrid and Collaborative Passage Rerankingcited by 0
  14. 2024Multi-word Term Embeddings Improve Lexical Product Retrievalcited by 0
  15. 2024GliLem: Leveraging GliNER for Contextualized Lemmatization in Estoniancited by 0