activity
20162026
most citedTo Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation

82 citations · 85 across the 13 of their papers we have counts for

collaborators
Showing cs.CLShow all

18 papers · 1 filter

cs.CL2026

Contrastive ESA: Human Evaluation of Multiple Translations at Once

Vilém Zouhar, Roman Grundkiewicz, Sara Rajaee +6

Current human evaluation of machine translation typically assesses single outputs in isolation, a paradigm that suffers from high annotator noise and cost. We introduce Contrastive…

cs.CL2026

AI translation of literary texts is "fine", but readers still prefer human translations

Yves Ferstler, Adam Podoxin, Ty Brassington +5

AI translation of literary works is increasingly common. While the content may be rendered adequately, we do not know enough about how readers experience it in terms of immersivene…

cs.CL2026

PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation

Lorenzo Proietti, Roman Grundkiewicz, Matt Post

We present PEAR (Pairwise Evaluation for Automatic Relative Scoring), a supervised quality estimation (QE) metric family that reframes reference-free machine translation (MT) evalu…

cs.CL2025

Preliminary Ranking of WMT25 General Machine Translation Systems

Tom Kocmi, Eleftherios Avramidis, Rachel Bawden +25

We present the preliminary rankings of machine translation (MT) systems submitted to the WMT25 General Machine Translation Shared Task, as determined by automatic evaluation metric…

cs.CL2024

On Instruction-Finetuning Neural Machine Translation Models

Vikas Raunak, Roman Grundkiewicz, Marcin Junczys-Dowmunt

In this work, we introduce instruction finetuning for Neural Machine Translation (NMT) models, which distills instruction following capabilities from Large Language Models (LLMs) i…

cs.CL2024

PyMarian: Fast Neural Machine Translation and Evaluation in Python

Thamme Gowda, Roman Grundkiewicz, Elijah Rippeth +2

The deep learning language of choice these days is Python; measured by factors such as available libraries and technical support, it is hard to beat. At the same time, software wri…