Tweeted By @DeepMind

While language models are capable of generating coherent texts, they can internalise social biases present in the training corpus. Bias extends to attributes (e.g., sentiment) of the generated text, though this can be reduced: https://t.co/B1ly3O2uwD, in Findings of #emnlp2020 pic.twitter.com/4N3HDslLDn

— DeepMind (@DeepMind) October 16, 2020