arXiv cs.CL· Eugene Matsumura, Yuki Arase·· 11 小时前AI 评分24
跨语言与多文本粒度的 CEFR 等级评估新方法
CEFR Level Assessment across Languages and Text Granularities
AI 导读
研究者提出一种统一训练目标，将 focal loss 与监督对比学习结合，用于文本 CEFR 等级自动评估，以缓解等级分布不均衡和相邻等级边界模糊的问题。该方法在句子级和文档级、单语与多语设置下均持续优于强基线，并在多个 CEFR 评估基准上取得新的 SOTA 表现。
正文 · 原文
Abstract:Automatic assessment of textual CEFR levels is an important task in educational natural language processing. However, accurate CEFR level prediction remains challenging due to the naturally imbalanced distribution of CEFR levels and the ambiguous boundaries between adjacent levels. To address these challenges, we propose a unified training objective that combines focal loss with supervised contrastive learning. Focal loss mitigates class imbalance by emphasizing underrepresented and difficult examples, while supervised contrastive learning learns more discriminative representations by encouraging intra-class compactness and inter-class separation. We evaluate the proposed method on sentence- and document-level CEFR assessment in both monolingual and multilingual settings. Experimental results demonstrate that our method consistently outperforms strong baselines across all settings, establishing new state-of-the-art performance on multiple CEFR assessment benchmarks.
| Comments: | 8 pages, 2 figures, 5 tables |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.41553 [cs.CL] |
| (or arXiv:2610.41553v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41553 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Eugene Matsumura [view email]
[v1]
Fri, 30 Oct 2026 10:50:38 UTC (363 KB)
来源：arXiv cs.CL · arxiv.org