Patrick Lewis

Patrick is a London-based Natural Language Processing PhD student, splitting his time between Facebook AI Research (FAIR) and University College London. Patrick is interested in how we can design neural natural language systems, which exploit human annotations much more effectively, particularly in question answering.

Patricks's Publications

June 19, 2020

RESEARCH

ML APPLICATIONS

Unsupervised Question Answering by Cloze Translation

Obtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what extent high quality training data is actually required for Extractive QA, and investigate the possibility of unsupervised Extractive QA…

Patrick Lewis, Ludovic Denoyer, Sebastian Riedel

June 19, 2020

June 19, 2020

RESEARCH

ML APPLICATIONS

Language Models as Knowledge Bases?

Recent progress in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks. Whilst learning linguistic knowledge, these models may also be storing relational knowledge present in the training data, and may be able to answer queries structured as “fill-in-the-blank” cloze statements…

Fabio Petroni, Tim Rocktäschel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, Alexander H. Miller, Sebastian Riedel

June 19, 2020