English

Dynamic Meta-Metrics: Source-Sentence Conditioned Weighting for MT Evaluation

Computation and Language 2026-05-12 v1

Abstract

We propose Dynamic Meta-Metrics (DMM), a framework for machine translation evaluation that learns source-sentence conditioned combinations of existing metrics. Rather than relying on a single static ensemble or language-specific weighting, DMM adapts the metric combination based on properties of the source segment. We study hard conditioning, which fits an interpretable combiner per cluster, and an exploratory soft-conditioned extension whose weights vary continuously with source-cluster responsibilities. We evaluate DMM on the WMT Metrics Shared Task data across multiple language pairs using pairwise agreement measures at the system and segment levels. Across settings, MLP-based combinations outperform linear and Gaussian process-based ensembles, and introducing soft conditioning yields gains over linear models.

Keywords

Cite

@article{arxiv.2605.09098,
  title  = {Dynamic Meta-Metrics: Source-Sentence Conditioned Weighting for MT Evaluation},
  author = {Luke Zhang and Justin Vasselli and Aditya Khan and York Hay Ng and En-Shiun Annie Lee},
  journal= {arXiv preprint arXiv:2605.09098},
  year   = {2026}
}

Comments

5 pages, ACL SRW 2026

R2 v1 2026-07-01T13:00:17.218Z