Follow
Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining. (arXiv:2009.11321v1 [cs.CL]) http://arxiv.org/abs/2009.11321
Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining. (arXiv:2009.11321v1 [cs.CL]) http://arxiv.org/abs/2009.11321