A contextualized CNN readout on BERT outperforms basic CNN and LSTM readouts on SQuAD 2.0, yet still underperforms vanilla BERT.
Understanding LSTM Networks
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
-
Exploring Neural Net Augmentation to BERT for Question Answering on SQUAD 2.0
A contextualized CNN readout on BERT outperforms basic CNN and LSTM readouts on SQuAD 2.0, yet still underperforms vanilla BERT.