Generalization in Generation: A closer look at Exposure Bias F Schmidt arXiv preprint arXiv:1910.00292, 2019 | 87 | 2019 |
Neural Document Embeddings for Intensive Care Patient Mortality Prediction P Grnarova, F Schmidt, SL Hyland, C Eickhoff arXiv preprint arXiv:1612.00467, 2016 | 64 | 2016 |
How does BERT capture semantics? A closer look at polysemous words D Yenicelik, F Schmidt, Y Kilcher Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting …, 2020 | 59 | 2020 |
Autoregressive Text Generation Beyond Feedback Loops F Schmidt, S Mandt, T Hofmann arXiv preprint arXiv:1908.11658, 2019 | 15 | 2019 |
Deep State Space Models for Unconditional Word Generation F Schmidt, T Hofmann Advances in Neural Information Processing Systems, 6158-6168, 2018 | 11 | 2018 |
BERT as a Teacher: Contextual Embeddings for Sequence-Level Reward F Schmidt, T Hofmann arXiv preprint arXiv:2003.02738, 2020 | 7 | 2020 |
Stochasticity and Non-Autoregressive Modeling in Deep Generative Models of Text F Schmidt ETH Zurich, 2020 | | 2020 |