A meta-learning methodology automates selection of textual representations from raw text, shown promising on 60 representations and over 80 text mining datasets for effective classification pipelines.
Initializing bayesian hyperparameter optimization via meta-learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Meta-learning of textual representations
A meta-learning methodology automates selection of textual representations from raw text, shown promising on 60 representations and over 80 text mining datasets for effective classification pipelines.