AIConfPaper
← Search

José G. C. de Souza

5 accepted papers

2024

Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation

Sweta Agrawal, José G. C. De Souza, Ricardo Rei, António Farinhas, Gonçalo Faria, Patrick Fernandes +2
EMNLP 2024main

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 quality. However, preference data based on human…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation

Gonçalo Faria, Sweta Agrawal, António Farinhas, Ricardo Rei, José G. C. de Souza, Andre Martins
NeurIPS 2024poster

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 metrics (such as COMET or BLEURT) exhibit high c…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

An Empirical Study of Translation Hypothesis Ensembling with Large Language Models

António Farinhas, José G. C. de Souza, Andre Martins
EMNLP 2023long main

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 problem of LLM-based machine translation. We experim…

Cited by 0Source ↗code ↗Scholar ↗
2023

Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning

Duarte Miguel Alves, Nuno M Guerreiro, João Alves, José Pombal, Ricardo Rei, José G. C. de Souza +2
EMNLP 2023short findings

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 due to overgeneration. Alternatives such as finetun…

Cited by 0Source ↗Scholar ↗
2022

Quality-Aware Decoding for Neural Machine Translation

Patrick Fernandes, António Farinhas, Ricardo Rei, José G. C. de Souza, Perez Ogayo, Graham Neubig +1
NAACL 2022long

Despite the progress in machine translation quality estimation and evaluation in the last years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers around finding the most probable translation according to the model (MAP decoding), approximated with beam search. In…

Cited by 87Source ↗PDF ↗code ↗Scholar ↗