AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models

Open paper
Benchmark Model Rank Results
end-to-end-dialogue-modelling-on-multiwoz-2-0AuGPT#2MultiWOZ (Success): 75.5MultiWOZ (Inform): 90.2BLEU: 17.2
end-to-end-dialogue-modelling-on-multiwoz-2-1AuGPT#3BLEU: 17.2MultiWOZ (Inform): 91.4MultiWOZ (Success): 72.9

Rank counts only results with a code link.