通过上下文对齐对比学习和岭集成改进词汇难度预测
Improving Lexical Difficulty Prediction with Context-Aligned Contrastive Learning and Ridge Ensembling
AI总结：
本文提出上下文对齐对比回归方法，结合岭回归集成与交叉视图上下文和有序软对比学习，提升跨语言词汇难度预测的准确性和稳定性。
摘要：
词汇难度预测是语言学习和可读性评估中的基础问题，要求模型估计不同母语背景下的词汇难度。然而，现有方法依赖于仅回归训练的标量监督，未能显式构建表示空间，限制了其捕捉跨语言对齐和有序难度的能力。为缓解这些问题，我们提出上下文对齐对比回归，整合岭回归集成与两个互补目标，即交叉视图上下文和有序软对比学习。在三个母语数据集上的实验表明，(i) 对比目标提高跨语言表示对齐并保留语言特定的细微差别，(ii) 学习的表示捕捉词汇难度的有序结构，(iii) 集成有效缓解了单个模型的系统偏差，使在难度层级上的表现更加稳定。
英文摘要：
Lexical difficulty prediction is a fundamental problem in language learning and readability assessment, requiring models to estimate word difficulty across different first-language (L1) backgrounds. However, existing approaches rely on regression-only training with scalar supervision, which does not explicitly structure the representation space, limiting their ability to capture cross-lingual alignment and ordinal difficulty. To mitigate these issues, we propose Context-Aligned Contrastive Regression, which integrates Ridge regression ensemble with two complementary objectives, i.e., Cross-View Context and Ordinal Soft Contrastive Learning. Experiments on three L1 datasets show that (i) contrastive objectives improve cross-lingual representation alignment while preserving language-specific nuances, (ii) the learned representations capture the ordinal structure of lexical difficulty, and (iii) the ensemble effectively mitigates systematic biases of individual models, leading to more stable performance across difficulty levels.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
