Patrick Lewis

Natural Language Processing Research Scientist

Natural Language Patrick

I’m a London-based AI and Natural Language Processing Research Scientist, currently working at Meta AI Research. Before this, I was a PhD student, splitting my time between Facebook AI Research (FAIR) and University College London.

I’m interested in how to represent, store and access knowledge and building more powerful, efficient and robust models for knowledge-intensive NLP tasks such as Question Answering and Fact Checking.

I also occasionally tweet here.

Selected Publications

All Publications >>

Patrick Lewis, Yuxiang Wu, Linqing Liu, Pasquale Minervini, Heinrich Küttler, Aleksandra Piktus, Pontus Stenetorp, Sebastian Riedel (2021). PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them. TACL 2021.

Preprint PDF Dataset Project Website

Patrick Lewis, Pontus Stenetorp, Sebastian Riedel (2020). Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets. EACL 2021.

Preprint PDF Dataset Project Website

Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. NeurIPS 2020.

Preprint PDF

Fabio Petroni, Patrick Lewis, Aleksandra Piktus, Tim Rocktäschel, Yuxiang Wu, Alexander H. Miller, Sebastian Riedel (2020). How Context Affects Language Models' Factual Predictions. AKBC 2020.

Preprint PDF

Fabio Petroni, Tim Rocktäschel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, Alexander H. Miller, Sebastian Riedel (2019). Language Models as Knowledge Bases?. In EMNLP 2019.

PDF Code Dataset Project

Latest Publications

More Publications

Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Dmytro Okhonko, Samuel Broscheit, Gautier Izacard, Patrick Lewis, Barlas Oğuz, Edouard Grave, Wen-tau Yih, Sebastian Riedel (2021). The Web Is Your Oyster -- Knowledge-Intensive NLP against a Very Large Web Corpus. Arxiv Preprint.

Preprint PDF

Patrick Lewis, Barlas Oğuz, Wenhan Xiong, Fabio Petroni, Wen-tau Yih, Sebastian Riedel (2021). Boosted Dense Retriever. Arxiv Preprint.

Preprint PDF

Xilun Chen, Kushal Lakhotia, Barlas Oğuz, Anchit Gupta, Patrick Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta, Wen-tau Yih (2021). Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?. Arxiv Preprint.

Preprint PDF