| Graph convolutional encoders for syntax-aware neural machine translation J Bastings, I Titov, W Aziz, D Marcheggiani, K Sima'an EMNLP, 2017 | 649 | 2017 |
| Scaling vision transformers to 22 billion parameters M Dehghani, J Djolonga, B Mustafa, P Padlewski, J Heek, J Gilmer, ... ICML, 2023 | 482 | 2023 |
| Exploiting semantics in neural machine translation with graph convolutional networks D Marcheggiani, J Bastings, I Titov NAACL, 2018 | 249 | 2018 |
| Interpretable neural predictions with differentiable binary variables J Bastings, W Aziz, I Titov ACL, 2019 | 241 | 2019 |
| The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? J Bastings, K Filippova EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2020 | 223 | 2020 |
| The language interpretability tool: Extensible, interactive visualizations and analysis for NLP models I Tenney, J Wexler, J Bastings, T Bolukbasi, A Coenen, S Gehrmann, ... EMNLP, 2020 | 212 | 2020 |
| Dissecting recall of factual associations in auto-regressive language models M Geva, J Bastings, K Filippova, A Globerson EMNLP, 2023 | 157 | 2023 |
| Scaling up models and data with t5x and seqio A Roberts, HW Chung, G Mishra, A Levskaya, J Bradbury, D Andor, ... JMLR 24 (377), 1-8, 2023 | 154 | 2023 |
| Joey NMT: A minimalist NMT toolkit for novices J Kreutzer, J Bastings, S Riezler EMNLP, 2019 | 129 | 2019 |
| Autoregressive diffusion models E Hoogeboom, AA Gritsenko, J Bastings, B Poole, R Berg, T Salimans ICLR, 2022 | 126 | 2022 |
| We Need to Talk About Random Splits A Søgaard, S Ebert, J Bastings, K Filippova EACL, 2021 | 108 | 2021 |
| The multiberts: Bert reproductions for robustness analysis T Sellam, S Yadlowsky, J Wei, N Saphra, A D'Amour, T Linzen, J Bastings, ... ICLR, 2022 | 91 | 2022 |
| Jump to better conclusions: SCAN both left and right J Bastings, M Baroni, J Weston, K Cho, D Kiela EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2018 | 76 | 2018 |
| "Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification J Bastings, S Ebert, P Zablotskaia, A Sandholm, K Filippova EMNLP, 2022 | 58 | 2022 |
| Training text-to-text transformers with privacy guarantees N Ponomareva, J Bastings, S Vassilvitskii Findings of the Association for Computational Linguistics: ACL 2022, 2182-2193, 2022 | 33 | 2022 |
| Diagnosing AI explanation methods with folk concepts of behavior A Jacovi, J Bastings, S Gehrmann, Y Goldberg, K Filippova JAIR 78, 459-489, 2023 | 23 | 2023 |
| Modeling latent sentence structure in neural machine translation J Bastings, W Aziz, I Titov, K Sima'an WNMT 2018 (Extended Abstract), 2018 | 8 | 2018 |
| All Fragments Count in Parser Evaluation J Bastings, K Sima'an LREC, 78-82, 2014 | 7 | 2014 |
| Low-Rank Adaptation for Multilingual Summarization: An Empirical Study C Whitehouse, F Huot, J Bastings, M Dehghani, CC Lin, M Lapata NAACL, 2024 | 5* | 2024 |
| Simple recurrence improves masked language models T Lei, R Tian, J Bastings, AP Parikh arXiv preprint arXiv:2205.11588, 2022 | 4 | 2022 |
Ivan TitovUniversity of Edinburgh / University of AmsterdamVerified email at inf.ed.ac.uk
