Zobrazeno 1 - 10
of 476
pro vyhledávání: '"Treviso, A."'
Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models, which enjoy
Externí odkaz:
http://arxiv.org/abs/2407.05489
Autor:
Treviso, Marcos, Guerreiro, Nuno M., Agrawal, Sweta, Rei, Ricardo, Pombal, José, Vaz, Tania, Wu, Helena, Silva, Beatriz, van Stigt, Daan, Martins, André F. T.
While machine translation (MT) systems are achieving increasingly strong performance on benchmarks, they often produce translations with errors and anomalies. Understanding these errors can potentially help improve the translation quality and user ex
Externí odkaz:
http://arxiv.org/abs/2406.19482
Autor:
Rei, Ricardo, Guerreiro, Nuno M., Pombal, José, van Stigt, Daan, Treviso, Marcos, Coheur, Luisa, de Souza, José G. C., Martins, André F. T.
We present the joint contribution of Unbabel and Instituto Superior T\'ecnico to the WMT 2023 Shared Task on Quality Estimation (QE). Our team participated on all tasks: sentence- and word-level quality prediction (task 1) and fine-grained error span
Externí odkaz:
http://arxiv.org/abs/2309.11925
Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these methods can be integrated to combi
Externí odkaz:
http://arxiv.org/abs/2305.17075
Autor:
Rei, Ricardo, Guerreiro, Nuno M., Treviso, Marcos, Coheur, Luisa, Lavie, Alon, Martins, André F. T.
Neural metrics for machine translation evaluation, such as COMET, exhibit significant improvements in their correlation with human judgments, as compared to traditional metrics based on lexical overlap, such as BLEU. Yet, neural metrics are, to a gre
Externí odkaz:
http://arxiv.org/abs/2305.11806
Autor:
Maria Eduarda Pasquotto Batista, Clayton Felipe da Silva Telles, Aline Aparecida da Silva Pierotto, Sofia Louise Santin Barilli, Katiane Rosa da Rocha, Rafael Ramon da Rosa, Brenda Carvalho Peradotto, Patricia Treviso
Publikováno v:
Brazilian Journal of Transplantation, Vol 27 (2024)
Objetivos: Conhecer as justificativas de familiares para a não autorização da doação de órgãos e tecidos. Métodos: Trata-se de um estudo documental. Analisaram-se os registros de entrevistas familiares de potenciais doadores, realizad
Externí odkaz:
https://doaj.org/article/ef77eff2fa8d42749d92911fa05e30ac
Autor:
Rei, Ricardo, Treviso, Marcos, Guerreiro, Nuno M., Zerva, Chrysoula, Farinha, Ana C., Maroti, Christine, de Souza, José G. C., Glushkova, Taisiya, Alves, Duarte M., Lavie, Alon, Coheur, Luisa, Martins, André F. T.
We present the joint contribution of IST and Unbabel to the WMT 2022 Shared Task on Quality Estimation (QE). Our team participated on all three subtasks: (i) Sentence and Word-level Quality Prediction; (ii) Explainable QE; and (iii) Critical Error De
Externí odkaz:
http://arxiv.org/abs/2209.06243
Autor:
Treviso, Marcos, Lee, Ji-Ung, Ji, Tianchu, van Aken, Betty, Cao, Qingqing, Ciosici, Manuel R., Hassid, Michael, Heafield, Kenneth, Hooker, Sara, Raffel, Colin, Martins, Pedro H., Martins, André F. T., Forde, Jessica Zosa, Milder, Peter, Simpson, Edwin, Slonim, Noam, Dodge, Jesse, Strubell, Emma, Balasubramanian, Niranjan, Derczynski, Leon, Gurevych, Iryna, Schwartz, Roy
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows. Such resources include data,
Externí odkaz:
http://arxiv.org/abs/2209.00099
Autor:
Ketlen Monteiro Mussart, Patrícia Treviso, Anelise Kirst da Silva, Sílvia Fátima Ferraboli, Thieli Lemos de Souza, Sofia Louise Santin Barilli
Publikováno v:
Escola Anna Nery, Vol 28 (2024)
Resumo Objetivo identificar a percepção de familiares e da equipe de enfermagem sobre a implementação de um diário de Unidade de Terapia Intensiva à rotina de cuidados do paciente crítico. Método estudo descritivo, qualitativo, realizado em u
Externí odkaz:
https://doaj.org/article/2fedaacadbce4239a920ba40c43f5a88
Autor:
Isabelle Cristinne Pinto Costa, Murilo César do Nascimento, Patrícia Treviso, Lucélia Terra Chini, Bartira de Aguiar Roza, Sayonara De Fátima Faria Barbosa, Karina Dal Sasso Mendes
Publikováno v:
Revista Latino-Americana de Enfermagem, Vol 32 (2024)
Objective: to map the scientific literature regarding the use of the Chat Generative Pre-trained Transformer, ChatGPT, in academic writing in health. Method: this was a scoping review, following the JBI methodology. Conventional databases and gray li
Externí odkaz:
https://doaj.org/article/80e29a7b3f0f4c5da017663065f286f6