| Language models as knowledge bases? F Petroni, T Rocktäschel, P Lewis, A Bakhtin, Y Wu, AH Miller, S Riedel EMNLP 2019, 2019 | 815 | 2019 |
| Dense passage retrieval for open-domain question answering V Karpukhin, B Oğuz, S Min, P Lewis, L Wu, S Edunov, D Chen, W Yih EMNLP 2020, 2020 | 775 | 2020 |
| Retrieval-augmented generation for knowledge-intensive nlp tasks P Lewis, E Perez, A Piktus, F Petroni, V Karpukhin, N Goyal, H Küttler, ... NeurIPS 2020, 2020 | 375 | 2020 |
| Mlqa: Evaluating cross-lingual extractive question answering P Lewis, B Oğuz, R Rinott, S Riedel, H Schwenk ACL 2020, 2019 | 219 | 2019 |
| KILT: a benchmark for knowledge intensive language tasks F Petroni, A Piktus, A Fan, P Lewis, M Yazdani, N De Cao, J Thorne, ... NAACL 2021, 2020 | 136 | 2020 |
| Interpretation of natural language rules in conversational machine reading M Saeidi, M Bartolo, P Lewis, S Singh, T Rocktäschel, M Sheldon, ... EMNLP 2018, 2018 | 102 | 2018 |
| Unsupervised question answering by cloze translation P Lewis, L Denoyer, S Riedel ACL 2019, 2019 | 101 | 2019 |
| Question and answer test-train overlap in open-domain question answering datasets P Lewis, P Stenetorp, S Riedel EACL 2021, 2020 | 99 | 2020 |
| How Context Affects Language Models' Factual Predictions F Petroni, P Lewis, A Piktus, T Rocktäschel, Y Wu, AH Miller, S Riedel AKBC 2020, 2020 | 71 | 2020 |
| Unsupervised question decomposition for question answering E Perez, P Lewis, W Yih, K Cho, D Kiela EMNLP 2020, 2020 | 69 | 2020 |
| Paq: 65 million probably-asked questions and what you can do with them P Lewis, Y Wu, L Liu, P Minervini, H Küttler, A Piktus, P Stenetorp, ... TACL 2021, 2021 | 58 | 2021 |
| Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval W Xiong, XL Li, S Iyer, J Du, P Lewis, WY Wang, Y Mehdad, W Yih, ... ICLR 2021, 2020 | 55* | 2020 |
| Pretrained language models for biomedical and clinical tasks: understanding and extending the state-of-the-art P Lewis, M Ott, J Du, V Stoyanov Proceedings of the 3rd Clinical Natural Language Processing Workshop, 146-157, 2020 | 47 | 2020 |
| NeurIPS 2020 EfficientQA competition: Systems, analyses and lessons learned S Min, J Boyd-Graber, C Alberti, D Chen, E Choi, M Collins, K Guu, ... PLMR Volume 133, 2021 | 42 | 2021 |
| Domain-matched pre-training tasks for dense retrieval B Oğuz, K Lakhotia, A Gupta, P Lewis, V Karpukhin, A Piktus, X Chen, ... arXiv preprint arXiv:2107.13602, 2021 | 19 | 2021 |
| The Web Is Your Oyster--Knowledge-Intensive NLP against a Very Large Web Corpus A Piktus, F Petroni, V Karpukhin, D Okhonko, S Broscheit, G Izacard, ... arXiv preprint arXiv:2112.09924, 2021 | 9 | 2021 |
| Understanding and predicting disease relationships through similarity fusion E Oerton, I Roberts, PSH Lewis, T Guilliams, A Bender Bioinformatics 35 (7), 1213-1220, 2019 | 9 | 2019 |
| Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? X Chen, K Lakhotia, B Oğuz, A Gupta, P Lewis, S Peshterliev, Y Mehdad, ... arXiv preprint arXiv:2110.06918, 2021 | 8 | 2021 |
| Challenges in generalization in open domain question answering L Liu, P Lewis, S Riedel, P Stenetorp arXiv preprint arXiv:2109.01156, 2021 | 6 | 2021 |
| Boosted dense retriever P Lewis, B Oğuz, W Xiong, F Petroni, W Yih, S Riedel NAACL 2022, 2021 | 5 | 2021 |
Sebastian RiedelProfessor @ University College London, Researcher @ Facebook AI ResearchVerified email at cs.ucl.ac.uk
