A masked-language-model pointwise mutual information score, with no fine-tuning on commonsense databases, matches or beats supervised baselines when mining novel Wikipedia triples, though the evaluation is weakened by test-set hyperparameter tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Commonsense Knowledge Mining from Pretrained Models
A masked-language-model pointwise mutual information score, with no fine-tuning on commonsense databases, matches or beats supervised baselines when mining novel Wikipedia triples, though the evaluation is weakened by test-set hyperparameter tuning.