| Earth Mover's Distance Pooling over Siamese LSTMs for Automatic Short Answer Grading. S Kumar, S Chakrabarti, S Roy IJCAI, 2046-2052, 2017 | 73 | 2017 |
| Von mises-fisher loss for training sequence to sequence models with continuous outputs S Kumar, Y Tsvetkov arXiv preprint arXiv:1812.04616, 2018 | 71 | 2018 |
| Controlled text generation as continuous optimization with multiple constraints S Kumar, E Malmi, A Severyn, Y Tsvetkov Advances in Neural Information Processing Systems 34, 14542-14554, 2021 | 46 | 2021 |
| Topics to avoid: Demoting latent confounds in text classification S Kumar, S Wintner, NA Smith, Y Tsvetkov arXiv preprint arXiv:1909.00453, 2019 | 33 | 2019 |
| Language generation models can cause harm: So what can we do about it? An actionable survey S Kumar, V Balachandran, L Njoo, A Anastasopoulos, Y Tsvetkov arXiv preprint arXiv:2210.07700, 2022 | 26 | 2022 |
| Gradient-based constrained sampling from language models S Kumar, B Paria, Y Tsvetkov Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022 | 22* | 2022 |
| Ssd-lm: Semi-autoregressive simplex-based diffusion language model for text generation and modular control X Han, S Kumar, Y Tsvetkov arXiv preprint arXiv:2210.17432, 2022 | 20 | 2022 |
| Machine translation into low-resource language varieties S Kumar, A Anastasopoulos, S Wintner, Y Tsvetkov arXiv preprint arXiv:2106.06797, 2021 | 18 | 2021 |
| Neural abstractive summarization with structural attention T Chowdhury, S Kumar, T Chakraborty arXiv preprint arXiv:2004.09739, 2020 | 15 | 2020 |
| On the blind spots of model-based evaluation metrics for text generation T He, J Zhang, T Wang, S Kumar, K Cho, J Glass, Y Tsvetkov arXiv preprint arXiv:2212.10020, 2022 | 12 | 2022 |
| Minding Language Models'(Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker M Sclar, S Kumar, P West, A Suhr, Y Choi, Y Tsvetkov arXiv preprint arXiv:2306.00924, 2023 | 11 | 2023 |
| Assessing language model deployment with risk cards L Derczynski, HR Kirk, V Balachandran, S Kumar, Y Tsvetkov, MR Leiser, ... arXiv preprint arXiv:2303.18190, 2023 | 10 | 2023 |
| A deep reinforced model for zero-shot cross-lingual summarization with bilingual semantic similarity rewards ZY Dou, S Kumar, Y Tsvetkov arXiv preprint arXiv:2006.15454, 2020 | 10 | 2020 |
| Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation M Sclar, P West, S Kumar, Y Tsvetkov, Y Choi arXiv preprint arXiv:2210.13800, 2022 | 5 | 2022 |
| An exploration of data augmentation techniques for improving english to tigrinya translation L Kidane, S Kumar, Y Tsvetkov arXiv preprint arXiv:2103.16789, 2021 | 5 | 2021 |
| A margin-based loss with synthetic negative samples for continuous-output machine translation G Bhat, S Kumar, Y Tsvetkov Proceedings of the 3rd Workshop on Neural Generation and Translation, 199-205, 2019 | 5 | 2019 |
| End-to-end differentiable GANs for text generation S Kumar, Y Tsvetkov PMLR, 2020 | 4 | 2020 |
| SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models X Han, S Kumar, Y Tsvetkov, M Ghazvininejad arXiv preprint arXiv:2305.14771, 2023 | 3 | 2023 |
| Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models O Ahia, S Kumar, H Gonen, J Kasai, DR Mortensen, NA Smith, Y Tsvetkov arXiv preprint arXiv:2305.13707, 2023 | 2 | 2023 |
| Accepted tutorials at the web conference 2022 R Tommasini, S Basu Roy, X Wang, H Wang, H Ji, J Han, P Nakov, ... Companion Proceedings of the Web Conference 2022, 391-399, 2022 | 2 | 2022 |
Yulia TsvetkovUniversity of WashingtonVerified email at cs.washington.edu
