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.
Commonsense mining as knowledge base completion? A study on the impact of novelty
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples. Inspired by the recent work by Li et al., we analyse if knowledge base completion models can be used to mine commonsense knowledge from raw text. We propose novelty of predicted triples with respect to the training set as an important factor in interpreting results. We critically analyse the difficulty of mining novel commonsense knowledge, and show that a simple baseline method outperforms the previous state of the art on predicting more novel.
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.