arXiv cs.CL· Phat Huu Ha, Nguyen Xuan Phuc, Nong Nhut Quy, Trinh Tran Tran, Nguyen Minh Triet, Dang Van Thin·· 13 小时前AI 评分21
专用决策模型在越南语上表现如何？一项文本分类实证研究
How Well Do Decision Models Transfer to Vietnamese? An Empirical Study of Text Classification
AI 导读
研究评估了四个专用决策模型在越南语零样本文本分类上的表现，覆盖六大任务组的 13 个分类设置。在英文标签描述下，JEV 整体表现最强，在 11 个设置中排名第一；双语标签描述未带来一致提升。鲁棒性实验显示，去除变音符号造成的性能下降最大，平均 macro-F1 下降 9.51–15.47 点，明显超过 teencode 和拼写错误的影响。
正文 · 原文
Abstract:Recent advances in specialized decision models have expanded the possibilities for zero-shot classification, yet their effectiveness on Vietnamese remains underexplored. This study evaluates four specialized decision models across 13 classification settings spanning six task groups, examining zero-shot performance, sensitivity to label-description language, and robustness to Vietnamese linguistic variations. The evaluation considers English, Vietnamese, and bilingual label descriptions, alongside common linguistic perturbations involving teencode, typographical errors, and diacritic removal. Under English label descriptions, JEV achieves the strongest overall performance, ranking first in 11 classification settings. The effects of label-description language vary across models and datasets, with bilingual descriptions providing no consistent improvement. Robustness experiments reveal that diacritic removal causes the most substantial performance degradation, reducing mean macro-$F_1$ by 9.51--15.47 points across model configurations, considerably more than teencode or typographical errors. These findings highlight the importance of label-description choices and Vietnamese orthographic variation when evaluating specialized decision models for zero-shot text classification.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.31422 [cs.CL] |
| (or arXiv:2610.31422v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31422 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Thin Dang Van [view email]
[v1]
Thu, 22 Oct 2026 15:24:16 UTC (85 KB)
来源：arXiv cs.CL · arxiv.org