mlsanityData to 7 Oct 2026

Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index

arXiv 1906.05807 ↗First posted 13 Jun 2019cs.CLcited by 64

Not on the map. Why?

Abstract (arXiv)

Existing open-domain question answering (QA) models are not suitable for real-time usage because they need to process several long documents on-demand for every input query. In this paper, we introduce the query-agnostic indexable representation of document phrases that can drastically speed up open-domain QA and also allows us to reach long-tail targets. In particular, our dense-sparse phrase encoding effectively captures syntactic, semantic, and lexical information of the phrases and eliminates the pipeline filtering of context documents. Leveraging optimization strategies, our model can be trained in a single 4-GPU server and serve entire Wikipedia (up to 60 billion phrases) under 2TB with CPUs only. Our experiments on SQuAD-Open show that our model is more accurate than DrQA (Chen et al., 2017) with 6000x reduced computational cost, which translates into at least 58x faster end-to-end inference benchmark on CPUs.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 18; 2023: 11; 2024: 11; 2025: 2; 2026: 2.

64 papers.

Sort:

By area:

  1. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  2. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  3. 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Timecited by 247
  4. 2022RealTime QA: What's the Answer Right Now?cited by 239
  5. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
  6. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  7. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  8. 2021NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learnedcited by 52
  9. 2021Learning to Retrieve Passages without Supervisioncited by 46
  10. 2022Nonparametric Masked Language Modelingcited by 39
  11. 2021Phrase Retrieval Learns Passage Retrieval, Toocited by 33
  12. 2024BERGEN: A Benchmarking Library for Retrieval-Augmented Generationcited by 31
38 more
  1. 2023Rethinking the Role of Token Retrieval in Multi-Vector Retrievalcited by 28
  2. 2022Decoupled Context Processing for Context Augmented Language Modelingcited by 24
  3. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  4. 2021Question Answering Infused Pre-training of General-Purpose Contextualized Representationscited by 19
  5. 2023Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representationscited by 19
  6. 2021Reasoning Over Virtual Knowledge Bases With Open Predicate Relationscited by 18
  7. 2024EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generationcited by 17
  8. 2022LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrievalcited by 15
  9. 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 12
  10. 2024RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Searchcited by 12
  11. 2022Improving Wikipedia Verifiability with AIcited by 11
  12. 2024Retrieval is Accurate Generationcited by 10
  13. 2023Talk the Walk: Synthetic Data Generation for Conversational Music Recommendationcited by 9
  14. 2023Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networkscited by 9
  15. 2021More Than Reading Comprehension: A Survey on Datasets and Metrics of Textual Question Answeringcited by 8
  16. 2021Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answeringcited by 8
  17. 2023Generator-Retriever-Generator Approach for Open-Domain Question Answeringcited by 8
  18. 2022Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographiescited by 7
  19. 2022A Study on the Efficiency and Generalization of Light Hybrid Retrieverscited by 7
  20. 2021Pruning the Index Contents for Memory Efficient Open-Domain QAcited by 6
  21. 2022Synthetic Target Domain Supervision for Open Retrieval QAcited by 6
  22. 2022Optimizing Test-Time Query Representations for Dense Retrievalcited by 6
  23. 2025VIBE: Vector Index Benchmark for Embeddingscited by 6
  24. 2021Simple Questions Generate Named Entity Recognition Datasetscited by 5
  25. 2024DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generationcited by 5
  26. 2026Anything2Skill: Compiling External Knowledge into Reusable Skills for Agentscited by 5
  27. 2022Two-Step Question Retrieval for Open-Domain QAcited by 4
  28. 2021Simple and Efficient ways to Improve REALMcited by 3
  29. 2022SpaceQA: Answering Questions about the Design of Space Missions and Space Craft Conceptscited by 3
  30. 2023KTRL+F: Knowledge-Augmented In-Document Searchcited by 3
  31. 2021EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering Systemcited by 2
  32. 2021What makes us curious? analysis of a corpus of open-domain questionscited by 2
  33. 2022Cross-Lingual Phrase Retrievalcited by 2
  34. 2022Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrievalcited by 2
  35. 2023Machine Reading Comprehension using Case-based Reasoningcited by 2
  36. 2023Phrase Retrieval for Open-Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learningcited by 2
  37. 2024Location Aware Modular Biencoder for Tourism Question Answeringcited by 2
  38. 2024JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuningcited by 2

50 most cited of 64 All 64 (JSON)