Search Results for author:
Found 3 papers, 0 papers with code
No offence, Bert -- I insult only humans! Multiple addressees sentence-level attack on toxicity detection neural network
We introduce a simple yet efficient sentence-level attack on black-box toxicity detector models.
On the definition of toxicity in NLP
The fundamental problem in toxicity detection task lies in the fact that the toxicity is ill-defined.
Named Entity Inclusion in Abstractive Text Summarization
After that, this model is used to mask named entities in the text and the BART model is trained to reconstruct them.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
