TACTICS：面向机器翻译的 taxonomy 感知智能语料采样方法

View PDF HTML (experimental)

Abstract:Large-scale machine-translation (MT) systems are typically evaluated on random samples from a corpus whose distributional composition is an artifact of how it was assembled. Such a sample inherits the phenomena the collection happens to contain rather than the full space a system must handle, spanning rule-governed conventions (terminology, punctuation, currency formatting) and context-dependent phenomena (tone, honorifics, document-level coherence), and thus provides no coverage guarantee for assessing robustness. We propose TACTICS (Taxonomy-Aware Coverage-opTimized Intelligent Corpus Sampling), which recasts coverage as an explicit objective. TACTICS induces a hierarchical taxonomy from a locale style guide, classifies segments against it, and selects a fixed-budget subset jointly optimizing coverage of rare categories, document-level coherence, and distributional fidelity to the full corpus. Applied to MT evaluation across four translation directions, TACTICS improves coverage of rare categories over lexical and embedding-based selection. By targeting the phenomena that separate systems, TACTICS makes a fixed evaluation budget go further, recovering the true system ranking from far fewer segments than random sampling wherever a real quality gap exists and never signaling a difference where none exists.

Comments:	Accepted at EMNLP 2026 (The Eleventh Conference in Machine Translation 2026 - WMT2026)
Subjects:	Computation and Language (cs.CL); Machine Learning (cs.LG)
Cite as:	arXiv:2609.17956 [cs.CL]
	(or arXiv:2609.17956v2 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2609.17956 arXiv-issued DOI via DataCite

Submission history

From: Prasanth Bathala [view email]
[v1] Wed, 16 Sep 2026 00:34:12 UTC (3,226 KB)
[v2] Thu, 1 Oct 2026 23:14:03 UTC (3,227 KB)