| Xlnet: Generalized autoregressive pretraining for language understanding Z Yang, Z Dai, Y Yang, J Carbonell, RR Salakhutdinov, QV Le Advances in neural information processing systems 32, 2019 | 4142 | 2019 |
| Transformer-xl: Attentive language models beyond a fixed-length context Z Dai, Z Yang, Y Yang, J Carbonell, QV Le, R Salakhutdinov arXiv preprint arXiv:1901.02860, 2019 | 1638 | 2019 |
| Revisiting semi-supervised learning with graph embeddings Z Yang, W Cohen, R Salakhudinov International conference on machine learning, 40-48, 2016 | 1079 | 2016 |
| Hotpotqa: A dataset for diverse, explainable multi-hop question answering Z Yang, P Qi, S Zhang, Y Bengio, WW Cohen, R Salakhutdinov, ... arXiv preprint arXiv:1809.09600, 2018 | 658 | 2018 |
| Multi-task cross-lingual sequence tagging from scratch Z Yang, R Salakhutdinov, W Cohen arXiv preprint arXiv:1603.06270, 2016 | 476* | 2016 |
| Gated-Attention Readers for Text Comprehension B Dhingra, H Liu, Z Yang, WW Cohen, R Salakhutdinov arXiv preprint arXiv:1606.01549, 2016 | 387 | 2016 |
| Good semi-supervised learning that requires a bad gan Z Dai, Z Yang, F Yang, WW Cohen, R Salakhutdinov arXiv preprint arXiv:1705.09783, 2017 | 364 | 2017 |
| Differentiable learning of logical rules for knowledge base reasoning F Yang, Z Yang, WW Cohen arXiv preprint arXiv:1702.08367, 2017 | 317 | 2017 |
| Review networks for caption generation Z Yang, Y Yuan, Y Wu, WW Cohen, RR Salakhutdinov Advances in neural information processing systems 29, 2361-2369, 2016 | 311* | 2016 |
| Breaking the softmax bottleneck: A high-rank RNN language model Z Yang, Z Dai, R Salakhutdinov, WW Cohen arXiv preprint arXiv:1711.03953, 2017 | 299 | 2017 |
| Cosnet: Connecting heterogeneous social networks with local and global consistency Y Zhang, J Tang, Z Yang, J Pei, PS Yu Proceedings of the 21th ACM SIGKDD international conference on knowledge …, 2015 | 258 | 2015 |
| Semi-supervised qa with generative domain-adaptive nets Z Yang, J Hu, R Salakhutdinov, WW Cohen arXiv preprint arXiv:1702.02206, 2017 | 137 | 2017 |
| Neural cross-lingual named entity recognition with minimal resources J Xie, Z Yang, G Neubig, NA Smith, J Carbonell arXiv preprint arXiv:1808.09861, 2018 | 118 | 2018 |
| Linguistic knowledge as memory for recurrent neural networks B Dhingra, Z Yang, WW Cohen, R Salakhutdinov arXiv preprint arXiv:1703.02620, 2017 | 99* | 2017 |
| Words or characters? fine-grained gating for reading comprehension Z Yang, B Dhingra, Y Yuan, J Hu, WW Cohen, R Salakhutdinov arXiv preprint arXiv:1611.01724, 2016 | 89 | 2016 |
| GPT Understands, Too X Liu, Y Zheng, Z Du, M Ding, Y Qian, Z Yang, J Tang arXiv preprint arXiv:2103.10385, 2021 | 68* | 2021 |
| Glomo: Unsupervised learning of transferable relational graphs Z Yang, JJ Zhao, B Dhingra, K He, WW Cohen, R Salakhutdinov, Y LeCun Proceedings of the 32nd International Conference on Neural Information …, 2018 | 51* | 2018 |
| Multi-modal bayesian embeddings for learning social knowledge graphs Z Yang, J Tang, W Cohen arXiv preprint arXiv:1508.00715, 2015 | 32 | 2015 |
| Mastering the dungeon: Grounded language learning by mechanical turker descent Z Yang, S Zhang, J Urbanek, W Feng, AH Miller, A Szlam, D Kiela, ... arXiv preprint arXiv:1711.07950, 2017 | 22 | 2017 |
| A probabilistic framework for location inference from social media Y Qian, J Tang, Z Yang, B Huang, W Wei, KM Carley arXiv preprint arXiv:1702.07281, 2017 | 21 | 2017 |
Ruslan SalakhutdinovUPMC Professor, Machine Learning Department, CMUVerified email at cs.cmu.edu
