An attention-based RNN with concatenated LSA n-gram features reaches 82.31% accuracy on PAN 2018 English gender prediction, a small gain over prior published results.
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
-
Gender Prediction from Tweets: Improving Neural Representations with Hand-Crafted Features
An attention-based RNN with concatenated LSA n-gram features reaches 82.31% accuracy on PAN 2018 English gender prediction, a small gain over prior published results.