ViConBERT：面向多义词与语义感知表示的语境-释义对齐越南语词嵌入 (ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations)

Recent advances in contextualized word embeddings have greatly improved semantic tasks such as Word Sense Disambiguation (WSD) and contextual similarity, but most progress has been limited to high-resource languages like English. Vietnamese, in contrast, still lacks robust models and evaluation resources for fine-grained semantic understanding. In this paper, we present ViConBERT, a novel framework for learning Vietnamese contextualized embeddings that integrates contrastive learning (SimCLR) and gloss-based distillation to better capture word meaning. We also introduce ViConWSD, the first large-scale synthetic dataset for evaluating semantic understanding in Vietnamese, covering both WSD and contextual similarity. Experimental results show that ViConBERT outperforms strong baselines on WSD (F1 = 0.87) and achieves competitive performance on ViCon (AP = 0.88) and ViSim-400 (Spearman's rho = 0.60), demonstrating its effectiveness in modeling both discrete senses and graded semantic relations. Our code, models, and data are available at https://github.com/tkhangg0910/ViConBERT

翻译：近年来，语境化词嵌入技术的进展显著提升了词义消歧（WSD）和语境相似性等语义任务的表现，但多数成果仅限于英语等高资源语言。相比之下，越南语仍缺乏用于细粒度语义理解的鲁棒模型与评估资源。本文提出ViConBERT，一种学习越南语语境化嵌入的新颖框架，该框架融合对比学习（SimCLR）与基于释义的知识蒸馏，以更好地捕捉词汇含义。我们还引入了ViConWSD，这是首个用于评估越南语语义理解的大规模合成数据集，涵盖词义消歧和语境相似性任务。实验结果表明，ViConBERT在词义消歧任务上（F1 = 0.87）优于强基线模型，并在ViCon（AP = 0.88）和ViSim-400（Spearman's rho = 0.60）上取得竞争性性能，证明了其在建模离散词义与渐进语义关系方面的有效性。我们的代码、模型与数据已公开于https://github.com/tkhangg0910/ViConBERT。