mlsanityData to 7 Oct 2026

Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach

arXiv 2010.01195 ↗First posted 2 Oct 2020cs.IRcited by 31

Not on the map. Why?

Abstract (arXiv)

Search engines often follow a two-phase paradigm where in the first stage (the retrieval stage) an initial set of documents is retrieved and in the second stage (the re-ranking stage) the documents are re-ranked to obtain the final result list. While deep neural networks were shown to improve the performance of the re-ranking stage in previous works, there is little literature about using deep neural networks to improve the retrieval stage. In this paper, we study the merits of combining deep neural network models and lexical models for the retrieval stage. A hybrid approach, which leverages both semantic (deep neural network-based) and lexical (keyword matching-based) retrieval models, is proposed. We perform an empirical study, using a publicly available TREC collection, which demonstrates the effectiveness of our approach and sheds light on the different characteristics of the semantic approach, the lexical approach, and their combination.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 3; 2024: 6; 2025: 8; 2026: 6.

31 papers.

Sort:

By area:

  1. 2022Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrievalcited by 26
  2. 2022UnifieR: A Unified Retriever for Large-Scale Retrievalcited by 19
  3. 2021Rethinking Search: Making Domain Experts out of Dilettantescited by 18
  4. 2022LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrievalcited by 15
  5. 2025Graph RAG-Tool Fusioncited by 15
  6. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systemscited by 15
  7. 2022Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Surveycited by 14
  8. 2025Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimizationcited by 10
  9. 2023Lexically-Accelerated Dense Retrievalcited by 7
  10. 2023CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrievalcited by 6
  11. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  12. 2024RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG Systemscited by 4
19 more
  1. 2025Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systemscited by 4
  2. 2024Multi-Field Adaptive Retrievalcited by 3
  3. 2022Hybrid Inverted Index Is a Robust Accelerator for Dense Retrievalcited by 2
  4. 2021Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independencecited by 1
  5. 2022Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systemscited by 1
  6. 2023MFBE: Leveraging Multi-Field Information of FAQs for Efficient Dense Retrievalcited by 1
  7. 2024Identification of Regulatory Requirements Relevant to Business Processes: A Comparative Study on Generative AI, Embedding-based Ranking, Crowd and Expert-driven Methodscited by 1
  8. 2024Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domaincited by 1
  9. 2025HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMscited by 1
  10. 2026Document Optimization for Black-Box Retrieval via Reinforcement Learningcited by 1
  11. 2026VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answeringcited by 1
  12. 2024Domain Adaptation of Multilingual Semantic Search -- Literature Reviewcited by 0
  13. 2024Knowledge Models for Cancer Clinical Practice Guidelines : Construction, Management and Usage in Question Answeringcited by 0
  14. 2025Modernizing Facebook Scoped Search: Keyword and Embedding Hybrid Retrieval with LLM Evaluationcited by 0
  15. 2025Rationale-Augmented Retrieval with Constrained LLM Re-Ranking for Task Discoverycited by 0
  16. 2026AutoIndex: Learning Representation Programs for Retrievalcited by 0
  17. 2026Do Static Embeddings Add Value to Hybrid Dutch Retrieval?cited by 0
  18. 2026LINE Conversation History Retrieval for Personal Memory RAG: Evaluating Search Representations and Hybrid Retrievalcited by 0
  19. 2026KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigationcited by 0