Recent research has shown that large language models (LLMs) can achieve remarkable
translation performance through supervised fine-tuning (SFT) using only a small amount of …

Vocabulary selection, or lexical shortlisting, is a well-known technique to improve latency of
Neural Machine Translation models by constraining the set of allowed output words during …

We propose XRAG, a novel benchmark designed to evaluate the generation abilities of LLMs
in cross-lingual Retrieval-Augmented Generation (RAG) settings where the user language …

Neural metrics trained on human evaluations of MT tend to correlate well with human
judgments, but their behavior is not fully understood. In this paper, we perform a controlled …

This paper describes Unbabel's submission to the WMT2019 APE Shared Task for the
English-German language pair. Following the recent rise of large, powerful, pre-trained models, …

We introduce OpenKiwi, a PyTorch-based open source framework for translation quality
estimation. OpenKiwi supports training and testing of word-level and sentence-level quality …

We present the contribution of the Unbabel team to the WMT 2019 Shared Task on Quality
Estimation. We participated on the word, sentence, and document-level tracks, encompassing …

In recent years, deep learning has revolutionized many areas of life as the driving technology
of artificial intelligence. One of the reasons for their success is their use of huge amounts of …

… A proposta consiste na filmagem em 360º com uma câmera de visão esférica Lady Bug (6
câmeras) da Point Grey Research, filmadora Sony Full HD e câmera Sony de alta resolução …

k-nearest-neighbor machine translation has demonstrated remarkable improvements in
machine translation quality by creating a datastore of cached examples. However, these …