| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, JB Alayrac, J Yu, R Soricut, J Schalkwyk, ... arXiv preprint arXiv:2312.11805, 2023 | 2209 | 2023 |
| Matching the blanks: Distributional similarity for relation learning LB Soares, N FitzGerald, J Ling, T Kwiatkowski arXiv preprint arXiv:1906.03158, 2019 | 967 | 2019 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ... arXiv preprint arXiv:2403.05530, 2024 | 699 | 2024 |
| A Joint Model of Language and Perception for Grounded Attribute Learning C Matuszek, N FitzGerald, L Zettlemoyer, L Bo, D Fox International Conference on Machine Learning, 2012 | 351 | 2012 |
| Semantic Role Labeling with Neural Network Factors N FitzGerald, O Täckström, K Ganchev, D Das Proceedings of the Conference on Empirical Methods in Natural Language …, 2015 | 175 | 2015 |
| Entities as experts: Sparse memory access with entity supervision T Févry, LB Soares, N FitzGerald, E Choi, T Kwiatkowski arXiv preprint arXiv:2004.07202, 2020 | 170 | 2020 |
| Large-Scale QA-SRL Parsing N FitzGerald, J Michael, L He, L Zettlemoyer Association of Computational Linguistics, 2018 | 118 | 2018 |
| Learning Distributions over Logical Forms for Referring Expression Generation N FitzGerald, Y Artzi, L Zettlemoyer Empirical Methods in Natural Language Processing, 2013 | 79 | 2013 |
| Long Short-Term Memory as a Dynamically Computed Element-wise Weighted Sum O Levy, K Lee, N FitzGerald, L Zettlemoyer Association of Computational Lingustics, 2018 | 53 | 2018 |
| Mention memory: incorporating textual knowledge into transformers through entity mention attention M De Jong, Y Zemlyanskiy, N FitzGerald, F Sha, W Cohen arXiv preprint arXiv:2110.06176, 2021 | 48 | 2021 |
| Semantic Parsing with Combinatory Categorial Grammars Y Artzi, N FitzGerald, L Zettlemoyer The Annual Meeting of the Association of Computational Linguistics, 2013 | 37 | 2013 |
| Empirical evaluation of pretraining strategies for supervised entity linking T Févry, N FitzGerald, LB Soares, T Kwiatkowski arXiv preprint arXiv:2005.14253, 2020 | 33 | 2020 |
| Learning cross-context entity representations from text J Ling, N FitzGerald, Z Shan, LB Soares, T Févry, D Weiss, T Kwiatkowski arXiv preprint arXiv:2001.03765, 2020 | 32 | 2020 |
| Fido: Fusion-in-decoder optimized for stronger performance and faster inference M de Jong, Y Zemlyanskiy, J Ainslie, N FitzGerald, S Sanghai, F Sha, ... arXiv preprint arXiv:2212.08153, 2022 | 27 | 2022 |
| Exploiting conversational features to detect high-quality blog comments N FitzGerald, G Carenini, G Murray, S Joty Advances in Artificial Intelligence: 24th Canadian Conference on Artificial …, 2011 | 16 | 2011 |
| MOLEMAN: mention-only linking of entities with a mention annotation network N FitzGerald, JA Botha, D Gillick, DM Bikel, T Kwiatkowski, A McCallum ACL 2021, 2021 | 12 | 2021 |
| MolClass: a web portal to interrogate diverse small molecule screen datasets with different computational models J Wildenhain, N FitzGerald, M Tyers Bioinformatics 28 (16), 2200-2201, 2012 | 11 | 2012 |
| User-adaptive visualizations: can gaze data tell us when a user needs them? C Conati, G Carenini, M Harati, D Tocker, N Fitzgerald, A Flagg Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011 | 9 | 2011 |
| Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute M De Jong, Y Zemlyanskiy, N FitzGerald, J Ainslie, S Sanghai, F Sha, ... International Conference on Machine Learning, 7329-7342, 2023 | 6 | 2023 |
| Interactive Learning and its Role in Pervasive Robotics C Matuszek, D Fox, N FitzGerald, E Herbst | 3 | 2012 |
Tom KwiatkowskiResearch Scientist, GoogleVerified email at google.com
