BART

Implemented By:

• TR Tobias Rohde
  tobiasr@allenai.org
  Allen Institute for Artificial Intelligence
• Dirk Groeneveld
  dirkg@allenai.org
  Allen Institute for Artificial Intelligence
  @mechanicaldirk
• Pete Walsh
  petew@allenai.org
  Allen Institute for Artificial Intelligence
  @epwalsh10

Description:

This is an implementation of the BART model from the paper BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. It uses a language modeling head and thus can be used for text generation.

This model is maintained by the AllenNLP team and its contributors on the AllenNLP models repository at https://github.com/allenai/allennlp-models.