A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

Open paper
Benchmark Model Rank Results
end-to-end-dialogue-modelling-on-multiwoz-2-1LABES-S2S#2BLEU: 18.3MultiWOZ (Inform): 78.1MultiWOZ (Success): 67.1

Rank counts only results with a code link.