Mika Juuti, Tommi Gröndahl, Adrian Flanagan, N Asokan
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Detection of some types of toxic language is hampered by extreme scarcity of labeled training data. Data augmentation -generating new synthetic data from a labeled seed datasetcan help. The efficacy of data augmentation on toxic language classification has not been fully explored. We present the first systematic study on how data augmentation techniques impact performance across toxic language classifiers, ranging from shallow logistic regression architectures to BERT -a state-of-the-art pretrained Transformer network. We compare the performance of eight techniques on very scarce seed datasets. We show that while BERT performed the best, shallow classifiers performed comparably when trained on data augmented with a combination of three techniques, including GPT-2-generated sentences. We discuss the interplay of performance and computational overhead, which can inform the choice of techniques under different constraints.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2009.12344")
get_code_for_paper("2009.12344")
have("2009.12344")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2009.12344.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2009.12344)
Connect an agent — have() is free.