TY - GEN

T1 - Locke’s Holiday

T2 - 2021 Conference on Empirical Methods in Natural Language Processing

AU - Søgaard, Anders

PY - 2021

Y1 - 2021

N2 - I highlight a simple failure mode of state-of-the-art machine reading systems: when contexts do not align with commonly shared beliefs. For example, machine reading systems fail to answer What did Elizabeth want? correctly in the context of ‘My kingdom for a cough drop, cried Queen Elizabeth.’ Biased by co-occurrence statistics in the training data of pretrained language models, systems predict my kingdom, rather than a cough drop. I argue such biases are analogous to human belief biases and present a carefully designed challenge dataset for English machine reading, called Auto-Locke, to quantify such effects. Evaluations of machine reading systems on Auto-Locke show the pervasiveness of belief bias in machine reading.

AB - I highlight a simple failure mode of state-of-the-art machine reading systems: when contexts do not align with commonly shared beliefs. For example, machine reading systems fail to answer What did Elizabeth want? correctly in the context of ‘My kingdom for a cough drop, cried Queen Elizabeth.’ Biased by co-occurrence statistics in the training data of pretrained language models, systems predict my kingdom, rather than a cough drop. I argue such biases are analogous to human belief biases and present a carefully designed challenge dataset for English machine reading, called Auto-Locke, to quantify such effects. Evaluations of machine reading systems on Auto-Locke show the pervasiveness of belief bias in machine reading.

U2 - 10.18653/v1/2021.emnlp-main.649

DO - 10.18653/v1/2021.emnlp-main.649

M3 - Article in proceedings

SP - 8240

EP - 8245

BT - Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics

Y2 - 7 November 2021 through 11 November 2021

ER -