# Two-Step Question Retrieval for Open-Domain QA

arXiv: https://arxiv.org/abs/2205.09393 · HTML: https://mlsanity.com/paper/2205.09393/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 19 May 2022.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Learning to Ask: Neural Question Generation for Reading Comprehension](https://mlsanity.com/paper/1705.00106/) (2017)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval](https://mlsanity.com/paper/2009.12756/) (2020)
- [Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets](https://mlsanity.com/paper/2008.02637/) (2020)
- [End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering](https://mlsanity.com/paper/2106.05346/) (2021)
- [Learning Dense Representations of Phrases at Scale](https://mlsanity.com/paper/2012.12624/) (2020)
- [Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index](https://mlsanity.com/paper/1906.05807/) (2019)
- [Efficient Passage Retrieval with Hashing for Open-domain Question Answering](https://mlsanity.com/paper/2106.00882/) (2021)
- [SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval](https://mlsanity.com/paper/2009.13013/) (2020)
- [Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering](https://mlsanity.com/paper/2004.11892/) (2020)
- [Phrase Retrieval Learns Passage Retrieval, Too](https://mlsanity.com/paper/2109.08133/) (2021)
- [Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering](https://mlsanity.com/paper/2101.00294/) (2021)
- [Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension](https://mlsanity.com/paper/1804.07726/) (2018)
- [Contextualized Sparse Representations for Real-Time Open-Domain Question Answering](https://mlsanity.com/paper/1911.02896/) (2019)

## Built on by (most cited first, 4 of 4)

- [When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively](https://mlsanity.com/paper/2404.19705/) (2024)
- [A Survey for Efficient Open Domain Question Answering](https://mlsanity.com/paper/2211.07886/) (2022)
- [QUADRo: Dataset and Models for QUestion-Answer Database Retrieval](https://mlsanity.com/paper/2304.01003/) (2023)
- [MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources](https://mlsanity.com/paper/2406.04670/) (2024)

## 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.