---
title: "Leveraging Passage Retrieval with Generative Models for Open"
description: "Closed-book generative QA models such as T5 store all their… 51.4 EM on NaturalQuestions. 35 references, cited by 649 papers here."
authors: ["Gautier Izacard", "Edouard Grave"]
year: 2021
venue: "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume"
source: "https://aclanthology.org/2021.eacl-main.74/"
doi: "10.18653/v1/2021.eacl-main.74"
arxiv: "2007.01282"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/izacard-2021-leveraging-passage-retrieval-generative-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/izacard-2021-leveraging-passage-retrieval-generative-models/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/) / Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

# Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

**Authors:** [Gautier Izacard](https://md.research.elamur.ai/free/en/authors/gautier-izacard/) and [Edouard Grave](https://md.research.elamur.ai/free/en/authors/edouard-grave/) · **Year:** 2021 · **Venue:** [Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2021](https://md.research.elamur.ai/free/en/venues/eacl/2021/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.eacl-main.74/) · [PDF](https://aclanthology.org/2021.eacl-main.74.pdf) · [DOI 10.18653/v1/2021.eacl-main.74](https://doi.org/10.18653/v1/2021.eacl-main.74) · [arXiv 2007.01282](https://arxiv.org/abs/2007.01282) · [OpenAlex](https://openalex.org/W3039017601)

**Citations:** 1,026 citations (OpenAlex, 2026-10-14) · [649](https://md.research.elamur.ai/free/en/papers/izacard-2021-leveraging-passage-retrieval-generative-models/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Closed-book generative QA models such as T5 store all their knowledge in their weights. They need billions of parameters to compete, which makes them costly to train and run. Izacard and Grave pair a retriever with a pretrained sequence-to-sequence reader. The retriever is BM25 for SQuAD and DPR for NaturalQuestions and TriviaQA, and it fetches 100-word Wikipedia passages. The reader is called Fusion-in-Decoder (FiD). The T5 encoder reads each passage separately, together with the question and the passage title. The decoder then attends over all the encoded passages at once to produce the answer. Because self-attention only covers one passage at a time, cost grows linearly with the number of passages rather than quadratically. As a result, the model can digest 100 passages. FiD sets new state-of-the-art exact-match scores on NaturalQuestions and TriviaQA. Accuracy keeps rising as more passages are added, whereas extractive readers tend to plateau. The work shows that a modest model with explicit text memory can beat a far larger closed-book one.

## Key points
- FiD-large (770M parameters) reaches 51.4 EM on NaturalQuestions and 67.6 EM on the TriviaQA open test set (80.1 on the hidden test). On SQuAD Open it scores 56.7 EM / 63.2 F1. FiD-base (220M) scores 48.2 / 65.0 / 53.4 on the same three benchmarks.
- On NQ, closed-book T5 with 11B parameters gets 36.6. FiD gets 44.1 with 770M parameters plus Wikipedia retrieved via BM25, at roughly comparable memory.
- Going from 10 to 100 retrieved passages adds about 6% on TriviaQA and 3.5% on NaturalQuestions. Earlier work reports most extractive models peaking around 10 to 20 passages.
- Setup:
  - Wikipedia is split into non-overlapping 100-word passages.
  - Retrieved passages are truncated to 250 word pieces.
  - Inputs are marked with `question:`, `title:` and `context:` tokens.
  - Answers are produced by greedy decoding.
  - Retrieval uses Lucene for BM25 and FAISS for DPR.
- Table 2 compares models trained with fewer passages, with and without a later finetuning step. With 5 training passages, NQ dev EM is 37.8 without finetuning and 45.0 with it, against 46.5 for full 100-passage training.

## Interesting ideas
- Encode each evidence chunk on its own and merge them only at the generation stage; this keeps cost linear in the number of chunks while still letting the answer draw on all of them together.
- Explicit, searchable text memory can stand in for huge parameter counts: a small reader plus a retrievable corpus beat a model over ten times larger.
- Training with a small evidence budget and then briefly finetuning with a larger one recovers most of the accuracy of full-budget training at lower cost.
- Scoring uses exact match against a list of acceptable answers after light normalization (lowercasing, dropping articles, punctuation and extra spaces).

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (world): Sentence-level frames could be built independently per sentence and only joined into the world of the text when a question arrives. Long tales would then not need a pairwise pass over every sentence.
- **I2** (world): This supports keeping knowledge in the inspectable compiled store (WordNet/FrameNet/Wikidata graph) and fetching relevant facts per question. Each answer could then cite the fact it used.
- **I3** (learn): Students could be trained first on short contexts or few witness parses, with a final short stage on full-size inputs, to save compute.
- **I4** (answer): School-test and fable-QA evaluation could accept several gold variants under a fixed normalizer. This avoids penalizing harmless surface differences while staying strict and reproducible.
- Simple role markers such as `question:`, `title:` and `context:` tell one model which part of a packed input plays which role. — (answer): When the reader receives the question plus selected world facts, explicit segment labels can keep provenance clear and make the reasoning trace easier to explain.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Meta](https://md.research.elamur.ai/free/en/companies/meta/) — Company, Menlo Park, United States · 158 works · 211,459 citations
- [Meta (United Kingdom)](https://md.research.elamur.ai/free/en/companies/meta-united-kingdom/) — Company, London, United Kingdom · 39 works · 11,541 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 1,282 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 523 works

🧭 Topics (2): [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 243 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 146 works

## Appears in

Agglomerations: [🏙️ London](https://md.research.elamur.ai/free/en/agglomerations/london/)

## Cite

Cite as: Gautier Izacard and Edouard Grave. 2021. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{izacard2021leveraging,
  title = {{Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering}},
  author = {Gautier Izacard and Edouard Grave},
  booktitle = {Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume},
  year = {2021},
  doi = {10.18653/v1/2021.eacl-main.74},
  eprint = {2007.01282},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2021.eacl-main.74}
}
```

- [← previous Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference](https://md.research.elamur.ai/free/en/papers/schick-2021-exploiting-cloze-questions-few-shot/)
- [next → Multitask Prompted Training Enables Zero-Shot Task Generalization](https://md.research.elamur.ai/free/en/papers/sanh-2021-multitask-prompted-training-enables-zero/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/)

## References

35 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. number of retrieved passages. In particular, we observe that increasing the number of passages from 10 to 100 leads to 6% improvement on TriviaQA and 3.5% improvement on NaturalQuestions. On the other hand, the performance of most extractive models seems to peak around 10 to 20 passages (Wang et al.… [find](https://scholar.google.com/scholar?q=number+of+retrieved+passages%2E+In+particular%2C+we+observe+that+increasing+the+number+of+passages+from+10+to+100+leads+to+6%25+improvement+on+TriviaQA+and+3%2E5%25+improvement+on+NaturalQuestions%2E+On+the+other)
2. Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017. [Reading Wikipedia to answer open-domain questions](https://md.research.elamur.ai/free/en/papers/chen-2017-reading-wikipedia-answer-open-domain/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1870–1879. \#\# Conclusion In this paper, we study a simple approach to open domain quest…
3. Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, and Caiming Xiong. 2020. [Learning to retrieve reasoning paths over wikipedia graph for question answering](https://md.research.elamur.ai/free/en/papers/asai-2019-learning-retrieve-reasoning-paths-over/). In International Conference on Learning Representations.
4. Tom B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). arXiv preprint arXiv:2005.14165.
5. Christopher Clark and Matt Gardner. 2018. [Simple and effective multi-paragraph reading comprehension](https://md.research.elamur.ai/free/en/papers/clark-2017-simple-effective-multi-paragraph-reading/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 845–855.
6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
7. Angela Fan, Yacine Jernite, Ethan Perez, David Grangier, Jason Weston, and Michael Auli. 2019. [ELI5: Long form question answering](https://md.research.elamur.ai/free/en/papers/fan-2019-eli5-long-form-question-answering/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3558–3567.
8. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. Realm: Retrieval-augmented language model pre-training. arXiv preprint arXiv:2002.08909. [find](https://scholar.google.com/scholar?q=Kelvin+Guu%2C+Kenton+Lee%2C+Zora+Tung%2C+Panupong+Pasupat%2C+and+Ming%2DWei+Chang%2E+2020%2E+Realm%3A+Retrieval%2Daugmented+language+model+pre%2Dtraining%2E+arXiv+preprint+arXiv%3A2002%2E08909%2E)
9. Zhengbao Jiang, Frank F. Xu, Jun Araki, and Graham Neubig. 2019. [How can we know what language models know?](https://md.research.elamur.ai/free/en/papers/jiang-2020-how-can-we-know-what/) arXiv preprint arXiv:1911.12543.
10. Mandar Joshi, Eunsol Choi, Daniel S. Weld, and Luke Zettlemoyer. 2017. [Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1601–1611.
11. Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. [Dense passage retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/). arXiv preprint arXiv:2004.04906.
12. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Jimmy+Ba%2E+2014%2E+Adam%3A+A+method+for+stochastic+optimization%2E+arXiv+preprint+arXiv%3A1412%2E6980%2E)
13. Tomáš Kočiskỳ, Jonathan Schwarz, Phil Blunsom, Chris Dyer, Karl Moritz Hermann, Gábor Melis, and Edward Grefenstette. 2018. [The NarrativeQA reading comprehension challenge](https://md.research.elamur.ai/free/en/papers/kocisky-2018-narrativeqa-reading-comprehension-challenge/). Transactions of the Association for Computational Linguistics, 6:317– 328.
14. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Red-field, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Matthew Kelcey, Jacob Devlin, Kenton Lee, Kristina N. Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. [Natural…](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/)
15. Jinhyuk Lee, Seongjun Yun, Hyunjae Kim, Miyoung Ko, and Jaewoo Kang. 2018. Ranking paragraphs for improving answer recall in open-domain question answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 565–569. [find](https://scholar.google.com/scholar?q=Jinhyuk+Lee%2C+Seongjun+Yun%2C+Hyunjae+Kim%2C+Miyoung+Ko%2C+and+Jaewoo+Kang%2E+2018%2E+Ranking+paragraphs+for+improving+answer+recall+in+open%2Ddomain+question+answering%2E+In+Proceedings+of+the+2018+Conference+on+Em)
16. Kenton Lee, Ming-Wei Chang, and Kristina Toutanova. 2019. [Latent retrieval for weakly supervised open domain question answering](https://md.research.elamur.ai/free/en/papers/lee-2019-latent-retrieval-weakly-supervised-open/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6086–6096.
17. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020a. [BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/). In Proceedings of the 58th Annual Meeting of th…
18. Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020b. Retrieval-augmented generation for knowledge-intensive nlp tasks. arXiv preprint arXiv:2005.11401. [find](https://scholar.google.com/scholar?q=Patrick+Lewis%2C+Ethan+Perez%2C+Aleksandara+Piktus%2C+Fabio+Petroni%2C+Vladimir+Karpukhin%2C+Naman+Goyal%2C+Heinrich+Ku%CC%88ttler%2C+Mike+Lewis%2C+Wen%2Dtau+Yih%2C+Tim+Rockta%CC%88schel%2C+et+al%2E+2020b%2E+Retrieval%2Daugmented+generati)
19. Sewon Min, Danqi Chen, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2019a. [A discrete hard EM approach for weakly supervised question answering](https://md.research.elamur.ai/free/en/papers/min-2019-discrete-hard-em-approach-weakly/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Proc…
20. Sewon Min, Danqi Chen, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2019b. [Knowledge guided text retrieval and reading for open domain question answering](https://md.research.elamur.ai/free/en/papers/chen-2020-open-domain-question-answering/). arXiv preprint arXiv:1911.03868.
21. Sewon Min, Julian Michael, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2020. AmbigQA: Answering ambiguous open-domain questions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 5783–5797. [find](https://scholar.google.com/scholar?q=Sewon+Min%2C+Julian+Michael%2C+Hannaneh+Hajishirzi%2C+and+Luke+Zettlemoyer%2E+2020%2E+AmbigQA%3A+Answering+ambiguous+open%2Ddomain+questions%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+La)
22. Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. [Deep contextualized word representations](https://md.research.elamur.ai/free/en/papers/peters-2018-deep-contextualized-word-representations/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolog…
23. Fabio Petroni, Tim Rocktäschel, Sebastian Riedel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander Miller. 2019. [Language models as knowledge bases?](https://md.research.elamur.ai/free/en/papers/petroni-2019-language-models-as-knowledge-bases/) In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural…
24. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Technical Report. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+Technical+Report%2E)
25. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of Machine Learning Research, 21(140):1–67.
26. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. [SQuAD: 100,000+ questions for machine comprehension of text](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392.
27. Siva Reddy, Danqi Chen, and Christopher D Manning. 2019. [CoQA: A conversational question answering challenge](https://md.research.elamur.ai/free/en/papers/reddy-2019-coqa-conversational-question-answering-challenge/). Transactions of the Association for Computational Linguistics, 7:249–266.
28. Adam Roberts, Colin Raffel, and Noam Shazeer. 2020. How much knowledge can you pack into the parameters of a language model? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 5418–5426. [find](https://scholar.google.com/scholar?q=Adam+Roberts%2C+Colin+Raffel%2C+and+Noam+Shazeer%2E+2020%2E+How+much+knowledge+can+you+pack+into+the+parameters+of+a+language+model%3F+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Langu)
29. Stephen E Robertson, Steve Walker, Susan Jones, Micheline M Hancock-Beaulieu, and Mike Gatford. 1995. [Okapi at TREC-3](https://md.research.elamur.ai/free/en/papers/robertson-1994-okapi-trec-3/). NIST Special Publication Sp.
30. Alon Talmor, Yanai Elazar, Yoav Goldberg, and Jonathan Berant. 2019. [oLMpics – on what language model pre-training captures](https://md.research.elamur.ai/free/en/papers/talmor-2019-olmpics-language-model-pre-training/). arXiv preprint arXiv:1912.13283.
31. Ellen M Voorhees. 1999. [The TREC-8 question answering track](https://md.research.elamur.ai/free/en/papers/voorhees-2000-trec-8-question-answering-track/) report. In Proceedings of the Eighth Text REtrieval Conference.
32. Shuohang Wang, Mo Yu, Xiaoxiao Guo, Zhiguo Wang, Tim Klinger, Wei Zhang, Shiyu Chang, Gerry Tesauro, Bowen Zhou, and Jing Jiang. 2018a. R 3 : Reinforced ranker-reader for open-domain question answering. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Shuohang+Wang%2C+Mo+Yu%2C+Xiaoxiao+Guo%2C+Zhiguo+Wang%2C+Tim+Klinger%2C+Wei+Zhang%2C+Shiyu+Chang%2C+Gerry+Tesauro%2C+Bowen+Zhou%2C+and+Jing+Jiang%2E+2018a%2E+R+3+%3A+Reinforced+ranker%2Dreader+for+open%2Ddomain+question+answerin)
33. Shuohang Wang, Mo Yu, Jing Jiang, Wei Zhang, Xiaoxiao Guo, Shiyu Chang, Zhiguo Wang, Tim Klinger, Gerald Tesauro, and Murray Campbell. 2018b. Evidence aggregation for answer re-ranking in open-domain question answering. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Shuohang+Wang%2C+Mo+Yu%2C+Jing+Jiang%2C+Wei+Zhang%2C+Xiaoxiao+Guo%2C+Shiyu+Chang%2C+Zhiguo+Wang%2C+Tim+Klinger%2C+Gerald+Tesauro%2C+and+Murray+Campbell%2E+2018b%2E+Evidence+aggregation+for+answer+re%2Dranking+in+open%2Ddomain+)
34. Zhiguo Wang, Patrick Ng, Xiaofei Ma, Ramesh Nallapati, and Bing Xiang. 2019. [Multi-passage BERT: A globally normalized BERT model for open-domain question answering](https://md.research.elamur.ai/free/en/papers/wang-2019-multi-passage-bert-globally-normalized/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference o…
35. Wei Yang, Yuqing Xie, Aileen Lin, Xingyu Li, Luchen Tan, Kun Xiong, Ming Li, and Jimmy Lin. 2019. [End-to-end open-domain question answering with BERTserini](https://md.research.elamur.ai/free/en/papers/yang-2019-end-end-open-domain-question/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 72…

*Updated 24 October 2026*