| CORD-19: The COVID-19 open research dataset LL Wang, K Lo, Y Chandrasekhar, R Reas, J Yang, D Eide, K Funk, ... Workshop on NLP for COVID-19, 2020 | 931* | 2020 |
| How language model hallucinations can snowball M Zhang, O Press, W Merrill, A Liu, NA Smith arXiv preprint arXiv:2305.13534, 2023 | 123 | 2023 |
| Competency problems: On finding and removing artifacts in language data M Gardner, W Merrill, J Dodge, ME Peters, A Ross, S Singh, N Smith Empirical Methods in Natural Language Processing, 2021 | 78 | 2021 |
| ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension S Subramanian, W Merrill, T Darrell, M Gardner, S Singh, A Rohrbach Empirical Methods in Natural Language Processing, 2022 | 70 | 2022 |
| A formal hierarchy of RNN architectures W Merrill, G Weiss, Y Goldberg, R Schwartz, NA Smith, E Yahav Association of Computational Linguistics, 2020 | 64 | 2020 |
| Provable limitations of acquiring meaning from ungrounded form: What will future language models understand? W Merrill, Y Goldberg, R Schwartz, NA Smith Transactions of the Association for Computational Linguistics 9, 1047-1060, 2021 | 62 | 2021 |
| Saturated transformers are constant-depth threshold circuits W Merrill, A Sabharwal, NA Smith Transactions of the Association for Computational Linguistics 10, 843-856, 2022 | 57 | 2022 |
| Sequential neural networks as automata W Merrill Deep Learning and Formal Languages (ACL workshop), 2019 | 56 | 2019 |
| Context-free transductions with neural stacks Y Hao, W Merrill, D Angluin, R Frank, N Amsel, A Benz, S Mendelsohn BlackboxNLP, 2018 | 34 | 2018 |
| The Parallelism Tradeoff: Limitations of Log-Precision Transformers W Merrill, A Sabharwal arXiv preprint arXiv:2207.00729, 2022 | 24* | 2022 |
| Effects of parameter norm growth during transformer training: Inductive bias from gradient descent W Merrill, V Ramanujan, Y Goldberg, R Schwartz, N Smith Empirical Methods in Natural Language Processing, 2021 | 22 | 2021 |
| A tale of two circuits: Grokking as competition of sparse and dense subnetworks W Merrill, N Tsilivis, A Shukla arXiv preprint arXiv:2303.11873, 2023 | 17 | 2023 |
| End-to-end graph-based TAG parsing with neural networks J Kasai, R Frank, P Xu, W Merrill, O Rambow NAACL, 2018 | 14 | 2018 |
| The Expressive Power of Transformers with Chain of Thought W Merrill, A Sabharwal arXiv preprint arXiv:2310.07923, 2023 | 11 | 2023 |
| Entailment Semantics Can Be Extracted from an Ideal Language Model W Merrill, A Warstadt, T Linzen CoNLL 2022, 2022 | 11 | 2022 |
| Formal language theory meets modern NLP W Merrill arXiv preprint arXiv:2102.10094, 2021 | 11 | 2021 |
| On the linguistic capacity of real-time counter automata W Merrill arXiv preprint arXiv:2004.06866, 2020 | 11 | 2020 |
| Transformers as recognizers of formal languages: A survey on expressivity L Strobl, W Merrill, G Weiss, D Chiang, D Angluin arXiv preprint arXiv:2311.00208, 2023 | 8 | 2023 |
| A Logic for Expressing Log-Precision Transformers W Merrill, A Sabharwal arXiv preprint arXiv:2210.02671, 2022 | 8* | 2022 |
| Finding hierarchical structure in neural stacks using unsupervised parsing W Merrill, L Khazan, N Amsel, Y Hao, S Mendelsohn, R Frank Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting …, 2019 | 7* | 2019 |
Noah A. SmithUniversity of Washington; Allen Institute for Artificial IntelligenceEmail verificata su cs.washington.edu
