| Toolformer: Language models can teach themselves to use tools T Schick, J Dwivedi-Yu, R Dessì, R Raileanu, M Lomeli, E Hambro, ... Advances in Neural Information Processing Systems 36, 2024 | 749 | 2024 |
| Word sequence kernels N Cancedda, E Gaussier, C Goutte, JM Renders The Journal of Machine Learning Research 3, 1059-1082, 2003 | 331 | 2003 |
| Estimating the sentence-level quality of machine translation systems L Specia, M Turchi, N Cancedda, N Cristianini, M Dymetman Proceedings of the 13th Annual conference of the European Association for …, 2009 | 318 | 2009 |
| Dynamic bi-phrases for statistical machine translation M Dymetman, WF Aziz, N Cancedda, JM Coursimault, V Nikoulina, ... US Patent 9,552,355, 2017 | 272 | 2017 |
| Method for aligning sentences at the word level enforcing selective contiguity constraints M Barbaiani, N Cancedda, CR Dance, SZ Fazekas, T Gaál, E Gaussier US Patent 9,020,804, 2015 | 243 | 2015 |
| System and method for productive generation of compound words in statistical machine translation N Cancedda, S Stymne US Patent 8,781,810, 2014 | 209 | 2014 |
| Estimation of parameters for machine translation without in-domain parallel data P Mathur, S Venkatapathy, N Cancedda US Patent 9,652,453, 2017 | 193 | 2017 |
| Method and apparatus for evaluating machine translation quality N Cancedda, K Yamada US Patent 7,587,307, 2009 | 128 | 2009 |
| Machine translation using non-contiguous fragments of text N Cancedda, B Cavestro, M Dymetman, E Gaussier, C Goutte, M Simard, ... US Patent 7,536,295, 2009 | 116 | 2009 |
| Multilingual autoregressive entity linking N De Cao, L Wu, K Popat, M Artetxe, N Goyal, M Plekhanov, ... Transactions of the Association for Computational Linguistics 10, 274-290, 2022 | 107 | 2022 |
| Translating with non-contiguous phrases M Simard, N Cancedda, B Cavestro, M Dymetman, E Gaussier, C Goutte, ... Proceedings of Human Language Technology Conference and Conference on …, 2005 | 97 | 2005 |
| Multi-domain machine translation model adaptation M Mylonakis, N Cancedda US Patent 9,235,567, 2016 | 95 | 2016 |
| Word alignment method and system for improved vocabulary coverage in statistical machine translation GA Hanneman, N Cancedda, M Dymetman US Patent 8,612,205, 2013 | 86 | 2013 |
| Method for computing similarity between text spans using factored word sequence kernels N Cancedda, P Mahé US Patent 8,077,984, 2011 | 85 | 2011 |
| Source-language entailment modeling for translating unknown terms S Mirkin, L Specia, N Cancedda, I Dagan, M Dymetman, I Szpektor Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL …, 2009 | 76 | 2009 |
| Learning machine translation C Goutte MIT Press, 2009 | 74 | 2009 |
| Machine translation using overlapping biphrase alignments and sampling B Roth, AR McCallum, M Dymetman, N Cancedda US Patent 8,775,155, 2014 | 70 | 2014 |
| Kernel Methods for Document Filtering. N Cancedda, C Goutte, JM Renders, N Cesa-Bianchi, A Conconi, Y Li, ... TREC 36, 132, 2002 | 67 | 2002 |
| Machine translation using elastic chunks N Cancedda, M Dymetman, E Gaussier, C Goutte US Patent 7,542,893, 2009 | 64 | 2009 |
| Method and apparatus for measuring similarity between documents N Cancedda US Patent 6,917,936, 2005 | 64 | 2005 |
Marc DymetmanIndependent Researcher (Prev. Principal Scientist, NAVER Labs Europe)E-mail confirmado em naverlabs.com
