| QuAC: Question answering in context E Choi, H He, M Iyyer, M Yatskar, W Yih, Y Choi, P Liang, L Zettlemoyer arXiv preprint arXiv:1808.07036, 2018 | 734 | 2018 |
| Delete, retrieve, generate: a simple approach to sentiment and style transfer J Li, R Jia, H He, P Liang arXiv preprint arXiv:1804.06437, 2018 | 544 | 2018 |
| Single image super-resolution using Gaussian process regression H He, WC Siu CVPR 2011, 449-456, 2011 | 369 | 2011 |
| Sharp nearby, fuzzy far away: How neural language models use context U Khandelwal, H He, P Qi, D Jurafsky arXiv preprint arXiv:1805.04623, 2018 | 320 | 2018 |
| Opponent modeling in deep reinforcement learning H He, J Boyd-Graber, K Kwok, H Daumé III International conference on machine learning, 1804-1813, 2016 | 319 | 2016 |
| FEQA: A question answering evaluation framework for faithfulness assessment in abstractive summarization E Durmus, H He, M Diab arXiv preprint arXiv:2005.03754, 2020 | 294 | 2020 |
| Learning to search in branch and bound algorithms H He, H Daume III, JM Eisner Advances in neural information processing systems 27, 2014 | 240 | 2014 |
| Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings H He, A Balakrishnan, M Eric, P Liang Association for Computational Linguistics (ACL), 2017 | 231 | 2017 |
| Gluoncv and gluonnlp: Deep learning in computer vision and natural language processing J Guo, H He, T He, L Lausen, M Li, H Lin, X Shi, C Wang, J Xie, S Zha, ... The Journal of Machine Learning Research 21 (1), 845-851, 2020 | 194 | 2020 |
| Unlearn dataset bias in natural language inference by fitting the residual H He, S Zha, H Wang arXiv preprint arXiv:1908.10763, 2019 | 172 | 2019 |
| An empirical study on robustness to spurious correlations using pre-trained language models L Tu, G Lalwani, S Gella, H He Transactions of the Association for Computational Linguistics 8, 621-633, 2020 | 145 | 2020 |
| Decoupling strategy and generation in negotiation dialogues H He, D Chen, A Balakrishnan, P Liang arXiv preprint arXiv:1808.09637, 2018 | 122 | 2018 |
| Imitation learning by coaching H He, J Eisner, H Daume Advances in neural information processing systems 25, 2012 | 122 | 2012 |
| Don’t until the final verb wait: Reinforcement learning for simultaneous machine translation A Grissom II, H He, J Boyd-Graber, J Morgan, H Daumé III Proceedings of the 2014 Conference on empirical methods in natural language …, 2014 | 102 | 2014 |
| Besting the quiz master: Crowdsourcing incremental classification games J Boyd-Graber, B Satinoff, H He, H Daumé III Proceedings of the 2012 joint conference on empirical methods in natural …, 2012 | 68 | 2012 |
| Pun generation with surprise H He, N Peng, P Liang arXiv preprint arXiv:1904.06828, 2019 | 67 | 2019 |
| Types of out-of-distribution texts and how to detect them U Arora, W Huang, H He arXiv preprint arXiv:2109.06827, 2021 | 66 | 2021 |
| Interpretese vs. translationese: The uniqueness of human strategies in simultaneous interpretation H He, J Boyd-Graber, H Daumé III Proceedings of the 2016 Conference of the North American Chapter of the …, 2016 | 60 | 2016 |
| Meta-learning via language model in-context tuning Y Chen, R Zhong, S Zha, G Karypis, H He arXiv preprint arXiv:2110.07814, 2021 | 59 | 2021 |
| Text generation by learning from demonstrations RY Pang, H He arXiv preprint arXiv:2009.07839, 2020 | 59 | 2020 |
Hal Daumé IIIAssociate Professor of Computer Science, University of MarylandVerified email at umiacs.umd.edu
