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

arXiv: https://arxiv.org/abs/1906.05807 · HTML: https://mlsanity.com/paper/1906.05807/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2019.

## Built on by (most cited first, 30 of 64)

- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://mlsanity.com/paper/2310.17157/) (2023)
- [RealTime QA: What's the Answer Right Now?](https://mlsanity.com/paper/2207.13332/) (2022)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [Dense X Retrieval: What Retrieval Granularity Should We Use?](https://mlsanity.com/paper/2312.06648/) (2023)
- [NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned](https://mlsanity.com/paper/2101.00133/) (2021)
- [Learning to Retrieve Passages without Supervision](https://mlsanity.com/paper/2112.07708/) (2021)
- [Nonparametric Masked Language Modeling](https://mlsanity.com/paper/2212.01349/) (2022)
- [Phrase Retrieval Learns Passage Retrieval, Too](https://mlsanity.com/paper/2109.08133/) (2021)
- [Rethinking the Role of Token Retrieval in Multi-Vector Retrieval](https://mlsanity.com/paper/2304.01982/) (2023)
- [BERGEN: A Benchmarking Library for Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01102/) (2024)
- [Decoupled Context Processing for Context Augmented Language Modeling](https://mlsanity.com/paper/2210.05758/) (2022)
- [A Survey for Efficient Open Domain Question Answering](https://mlsanity.com/paper/2211.07886/) (2022)
- [Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations](https://mlsanity.com/paper/2311.04335/) (2023)
- [Question Answering Infused Pre-training of General-Purpose Contextualized Representations](https://mlsanity.com/paper/2106.08190/) (2021)
- [Reasoning Over Virtual Knowledge Bases With Open Predicate Relations](https://mlsanity.com/paper/2102.07043/) (2021)
- [EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.12559/) (2024)
- [LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval](https://mlsanity.com/paper/2208.13661/) (2022)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2103.03125/) (2021)
- [RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2408.08933/) (2024)
- [Improving Wikipedia Verifiability with AI](https://mlsanity.com/paper/2207.06220/) (2022)
- [Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation](https://mlsanity.com/paper/2301.11489/) (2023)
- [Retrieval is Accurate Generation](https://mlsanity.com/paper/2402.17532/) (2024)
- [Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks](https://mlsanity.com/paper/2301.12847/) (2023)
- [More Than Reading Comprehension: A Survey on Datasets and Metrics of Textual Question Answering](https://mlsanity.com/paper/2109.12264/) (2021)
- [Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2110.01599/) (2021)
- [Generator-Retriever-Generator Approach for Open-Domain Question Answering](https://mlsanity.com/paper/2307.11278/) (2023)
- [Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographies](https://mlsanity.com/paper/2204.05879/) (2022)

## 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.