Papers
arxiv:2511.12249

ViConBERT: Context-Gloss Aligned Vietnamese Word Embedding for Polysemous and Sense-Aware Representations

Published on Nov 15
Authors:
,
,

Abstract

ViConBERT, integrating contrastive learning and gloss-based distillation, enhances Vietnamese contextual embeddings, achieving strong performance in Word Sense Disambiguation and contextual similarity.

AI-generated summary

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

Community

Sign up or log in to comment

Models citing this paper 2

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2511.12249 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.