More training data and larger LSTM hidden layers yield diminishing returns on subject-verb agreement accuracy, and GPT and BERT sometimes score below LSTMs trained on far less data.
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
-
Quantity doesn't buy quality syntax with neural language models
More training data and larger LSTM hidden layers yield diminishing returns on subject-verb agreement accuracy, and GPT and BERT sometimes score below LSTMs trained on far less data.