mlsanityData to 7 Oct 2026

Two-Step Question Retrieval for Open-Domain QA

arXiv 2205.09393 ↗First posted 19 May 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

The retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle this problem by indexing question-answer pairs and searching for similar questions. These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models. This paper proposes a two-step question retrieval model, SQuID (Sequential Question-Indexed Dense retrieval) and distant supervision for training. SQuID uses two bi-encoders for question retrieval. The first-step retriever selects top-k similar questions, and the second-step retriever finds the most similar question from the top-k questions. We evaluate the performance and the computational efficiency of SQuID. The results show that SQuID significantly increases the performance of existing question retrieval models with a negligible loss on inference speed.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 27 references that are in the map. First posted on arXiv 19 May 2022.

Builds on

24 of 27 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  9. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  10. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
  11. 2017Learning to Ask: Neural Question Generation for Reading Comprehensioncited by 186
  12. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
12 more
  1. 2020Answering Complex Open-Domain Questions with Multi-Hop Dense Retrievalcited by 160
  2. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  3. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  4. 2020Learning Dense Representations of Phrases at Scalecited by 91
  5. 2019Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Indexcited by 64
  6. 2021Efficient Passage Retrieval with Hashing for Open-domain Question Answeringcited by 53
  7. 2020SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrievalcited by 50
  8. 2020Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answeringcited by 39
  9. 2021Phrase Retrieval Learns Passage Retrieval, Toocited by 33
  10. 2021Rider: Reader-Guided Passage Reranking for Open-Domain Question Answeringcited by 28
  11. 2018Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehensioncited by 23
  12. 2019Contextualized Sparse Representations for Real-Time Open-Domain Question Answeringcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 2.

4 papers.

  1. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  2. 2024When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectivelycited by 20
  3. 2023QUADRo: Dataset and Models for QUestion-Answer Database Retrievalcited by 5
  4. 2024MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sourcescited by 2