Rationalizing Neural Predictions T Lei, R Barzilay, T Jaakkola EMNLP, 2016 | 925 | 2016 |
Style Transfer from Non-parallel Text by Cross-alignment T Shen, T Lei, R Barzilay, T Jaakkola NeurIPS, 6830-6841, 2017 | 869 | 2017 |
Simple Recurrent Units for Highly Parallelizable Recurrence T Lei, Y Zhang, SI Wang, H Dai, Y Artzi EMNLP, 2018 | 505* | 2018 |
Structured Pruning of Large Language Models Z Wang, J Wohlwend, T Lei EMNLP, 2020 | 220 | 2020 |
Molding CNNs for Text: Non-linear, Non-consecutive Convolutions T Lei, R Barzilay, T Jaakkola EMNLP, 2015 | 168 | 2015 |
Mixture-of-experts with expert choice routing Y Zhou, T Lei, H Liu, N Du, Y Huang, V Zhao, A Dai, Z Chen, Q Le, ... NeurIPS, 2022 | 156 | 2022 |
Deriving Neural Architectures from Sequence and Graph Kernels T Lei, W Jin, R Barzilay, T Jaakkola ICML, 2017 | 147 | 2017 |
Low-Rank Tensors for Scoring Dependency Structures T Lei, Y Xin, Y Zhang, R Barzilay, T Jaakkola ACL, 2014 | 128 | 2014 |
Semi-supervised Question Retrieval with Gated Convolutions T Lei, H Joshi, R Barzilay, T Jaakkola, K Tymoshenko, A Moschitti, ... NAACL, 2016 | 121 | 2016 |
Training language models with memory augmentation Z Zhong, T Lei, D Chen EMNLP, 2022 | 101 | 2022 |
Learning High-level Planning from Text SRK Branavan, N Kushman, T Lei, R Barzilay ACL, 2012 | 87 | 2012 |
Adversarial Domain Adaptation for Duplicate Question Detection DJ Shah, T Lei, A Moschitti, S Romeo, P Nakov EMNLP, 2018 | 83 | 2018 |
Maintaining quality of customer support messages JE Hackman, S Henry, AN Hampton, T Lei US Patent 10,489,792, 2019 | 81 | 2019 |
From Natural Language Specifications to Program Input Parsers T Lei, F Long, R Barzilay, M Rinard ACL, 1294-1303, 2013 | 80 | 2013 |
When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute T Lei EMNLP, 2021 | 61 | 2021 |
Greed is Good if Randomized: New Inference for Dependency Parsing Y Zhang, T Lei, R Barzilay, T Jaakkola EMNLP, 1013-1024, 2014 | 59 | 2014 |
On Optimization of Expertise Matching with Various Constraints W Tang, J Tang, T Lei, C Tan, B Gao, T Li Neurocomputing 76 (1), 71-83, 2012 | 54 | 2012 |
Mm1: Methods, analysis & insights from multimodal llm pre-training B McKinzie, Z Gan, JP Fauconnier, S Dodge, B Zhang, P Dufter, D Shah, ... arXiv preprint arXiv:2403.09611, 2024 | 50 | 2024 |
High-order Low-rank Tensors for Semantic Role Labeling T Lei, Y Zhang, L Màrquez, A Moschitti, R Barzilay NAACL, 2015 | 47 | 2015 |
Colt5: Faster long-range transformers with conditional computation J Ainslie, T Lei, M de Jong, S Ontañón, S Brahma, Y Zemlyanskiy, ... arXiv preprint arXiv:2303.09752, 2023 | 44 | 2023 |