Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Souza, P. G. C."'
Autor:
Mohammed, Wafaa, Agrawal, Sweta, Farajian, M. Amin, Cabarrão, Vera, Eikema, Bryan, Farinha, Ana C., de Souza, José G. C.
This paper presents the findings from the third edition of the Chat Translation Shared Task. As with previous editions, the task involved translating bilingual customer support conversations, specifically focusing on the impact of conversation contex
Externí odkaz:
http://arxiv.org/abs/2410.11624
Autor:
Agrawal, Sweta, de Souza, José G. C., Rei, Ricardo, Farinhas, António, Faria, Gonçalo, Fernandes, Patrick, Guerreiro, Nuno M, Martins, Andre
Alignment with human preferences is an important step in developing accurate and safe large language models. This is no exception in machine translation (MT), where better handling of language nuances and context-specific variations leads to improved
Externí odkaz:
http://arxiv.org/abs/2410.07779
Autor:
Martins, Pedro Henrique, Fernandes, Patrick, Alves, João, Guerreiro, Nuno M., Rei, Ricardo, Alves, Duarte M., Pombal, José, Farajian, Amin, Faysse, Manuel, Klimaszewski, Mateusz, Colombo, Pierre, Haddow, Barry, de Souza, José G. C., Birch, Alexandra, Martins, André F. T.
The quality of open-weight LLMs has seen significant improvement, yet they remain predominantly focused on English. In this paper, we introduce the EuroLLM project, aimed at developing a suite of open-weight multilingual LLMs capable of understanding
Externí odkaz:
http://arxiv.org/abs/2409.16235
Autor:
Faria, Gonçalo R. A., Agrawal, Sweta, Farinhas, António, Rei, Ricardo, de Souza, José G. C., Martins, André F. T.
An important challenge in machine translation (MT) is to generate high-quality and diverse translations. Prior work has shown that the estimated likelihood from the MT model correlates poorly with translation quality. In contrast, quality evaluation
Externí odkaz:
http://arxiv.org/abs/2406.00049
Autor:
Alves, Duarte M., Pombal, José, Guerreiro, Nuno M., Martins, Pedro H., Alves, João, Farajian, Amin, Peters, Ben, Rei, Ricardo, Fernandes, Patrick, Agrawal, Sweta, Colombo, Pierre, de Souza, José G. C., Martins, André F. T.
While general-purpose large language models (LLMs) demonstrate proficiency on multiple tasks within the domain of translation, approaches based on open LLMs are competitive only when specializing on a single task. In this paper, we propose a recipe f
Externí odkaz:
http://arxiv.org/abs/2402.17733
Autor:
Alves, Duarte M., Guerreiro, Nuno M., Alves, João, Pombal, José, Rei, Ricardo, de Souza, José G. C., Colombo, Pierre, Martins, André F. T.
Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often require extra post-processing du
Externí odkaz:
http://arxiv.org/abs/2310.13448
Large language models (LLMs) are becoming a one-fits-many solution, but they sometimes hallucinate or produce unreliable output. In this paper, we investigate how hypothesis ensembling can improve the quality of the generated text for the specific pr
Externí odkaz:
http://arxiv.org/abs/2310.11430
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
Autor:
Fernandes, Patrick, Madaan, Aman, Liu, Emmy, Farinhas, António, Martins, Pedro Henrique, Bertsch, Amanda, de Souza, José G. C., Zhou, Shuyan, Wu, Tongshuang, Neubig, Graham, Martins, André F. T.
Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that generate toxic, inaccurate, and unhelpful content, and automatic evaluation
Externí odkaz:
http://arxiv.org/abs/2305.00955
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