| TBD | (直播-Discussion) <br> ALBERT |||[ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942)||
| TBD | (直播-Paper) <br> |||[Dropout as a Bayesian Approximation:Representing Model Uncertainty in Deep Learning](https://arxiv.org/pdf/1506.02142.pdf)||