%0 Conference Proceedings %T Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly %A Kassner, Nora %A Schütze, Hinrich %Y Jurafsky, Dan %Y Chai, Joyce %Y Schluter, Natalie %Y Tetreault, Joel %S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics %D 2020 %8 July %I Association for Computational Linguistics %C Online %F kassner-schutze-2020-negated %X Building on Petroni et al. 2019, we propose two new probing tasks analyzing factual knowledge stored in Pretrained Language Models (PLMs). (1) Negation. We find that PLMs do not distinguish between negated (“Birds cannot [MASK]”) and non-negated (“Birds can [MASK]”) cloze questions. (2) Mispriming. Inspired by priming methods in human psychology, we add “misprimes” to cloze questions (“Talk? Birds can [MASK]”). We find that PLMs are easily distracted by misprimes. These results suggest that PLMs still have a long way to go to adequately learn human-like factual knowledge. %R 10.18653/v1/2020.acl-main.698 %U https://aclanthology.org/2020.acl-main.698 %U https://doi.org/10.18653/v1/2020.acl-main.698 %P 7811-7818