Zobrazeno 1 - 10
of 332
pro vyhledávání: '"Vilar, David"'
Recent research in neural machine translation (NMT) has shown that training on high-quality machine-generated data can outperform training on human-generated data. This work accompanies the first-ever release of a LLM-generated, MBR-decoded and QE-re
Externí odkaz:
http://arxiv.org/abs/2408.06537
Minimum Bayes Risk (MBR) decoding is a powerful decoding strategy widely used for text generation tasks, but its quadratic computational complexity limits its practical application. This paper presents a novel approach for approximating MBR decoding
Externí odkaz:
http://arxiv.org/abs/2406.02832
Autor:
Peter, Jan-Thorsten, Vilar, David, Deutsch, Daniel, Finkelstein, Mara, Juraska, Juraj, Freitag, Markus
Quality Estimation (QE), the evaluation of machine translation output without the need of explicit references, has seen big improvements in the last years with the use of neural metrics. In this paper we analyze the viability of using QE metrics for
Externí odkaz:
http://arxiv.org/abs/2311.05350
Autor:
Tomani, Christian, Vilar, David, Freitag, Markus, Cherry, Colin, Naskar, Subhajit, Finkelstein, Mara, Garcia, Xavier, Cremers, Daniel
Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models. The underlying assumption is that model probability correlates well with human judgment, with better translations getting assig
Externí odkaz:
http://arxiv.org/abs/2310.06707
Large language models (LLMs) that have been trained on multilingual but not parallel text exhibit a remarkable ability to translate between languages. We probe this ability in an in-depth study of the pathways language model (PaLM), which has demonst
Externí odkaz:
http://arxiv.org/abs/2211.09102
We address efficient calculation of influence functions for tracking predictions back to the training data. We propose and analyze a new approach to speeding up the inverse Hessian calculation based on Arnoldi iteration. With this improvement, we ach
Externí odkaz:
http://arxiv.org/abs/2112.03052
Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e.g. containing contents from multiple domains or different levels of quality or complexity. Naturally, these facets do no
Externí odkaz:
http://arxiv.org/abs/2110.06997
Autor:
Domhan, Tobias, Denkowski, Michael, Vilar, David, Niu, Xing, Hieber, Felix, Heafield, Kenneth
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of the art model architectures, dis
Externí odkaz:
http://arxiv.org/abs/2008.04885
Autor:
Fernandez-Crespo, Silvia, Vazquez-Agra, Nestor, Marques-Afonso, Ana-Teresa, Cruces-Sande, Anton, Martinez-Olmos, Miguel-Angel, Araujo-Vilar, David, Hermida-Ameijeiras, Alvaro
Publikováno v:
In Medicina Clinica 7 December 2023 161(11):470-475
Autor:
Cobelo-Gómez, Silvia, Sánchez-Iglesias, Sofía, Rábano, Alberto, Senra, Ana, Aguiar, Pablo, Gómez-Lado, Noemí, García-Varela, Lara, Burgueño-García, Iván, Lampón-Fernández, Laura, Fernández-Pombo, Antía, Díaz-López, Everardo Josué, Prado-Moraña, Teresa, San Millán, Beatriz, Araújo-Vilar, David
Publikováno v:
In Neurobiology of Disease 15 October 2023 187