we extend the LAMA (Petroni et al., 2019)
evaluation framework by a component that is
focused on negation.
BERT is Not a Knowledge Base (Yet): Factual Knowledge vs. Name-Based Reasoning in Unsupervised QA (short paper)https://arxiv.org/abs/1911.03681
We take issue with this interpretation and argue that the performance of BERT is
partly due to reasoning about (the surface form
of) entity names, e.g., guessing that a person
with an Italian-sounding name speaks Italian.
More specifically, we show that BERT’s precision drops dramatically when we filter certain
easy-to-guess facts
Negated LAMA: Birds cannot fly (short paper) https://arxiv.org/abs/1911.03343
BERT is Not a Knowledge Base (Yet): Factual Knowledge vs. Name-Based Reasoning in Unsupervised QA (short paper) https://arxiv.org/abs/1911.03681
Join on Hangout: https://hangouts.google.com/group/kUxBAunjGittAkBUA