Assigning separate MQM error categories to different AI agents, then merging their annotations with an editor agent, improved machine translation scores over zero-shot and single-agent baselines, with model-dependent human preference.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MAATS: A Multi-Agent Automated Translation System Based on MQM Evaluation
Assigning separate MQM error categories to different AI agents, then merging their annotations with an editor agent, improved machine translation scores over zero-shot and single-agent baselines, with model-dependent human preference.