VLUE

VLUE是越南国家大学胡志明市信息技术大学推出的首个越南语言理解评估基准，包含五个不同任务的数据集，涵盖文本分类、跨度提取和自然语言理解等。数据集大小、数据量和Tokens数各异，来源于越南的Wikipedia、社交网络和文章。创建过程中，研究团队精心选择了具有挑战性但可解决的任务，确保数据集的多样性和实用性。VLUE旨在为越南NLP领域提供一个标准化的评估框架，解决模型评估和比较的问题，推动越南语言理解技术的进步。

VLUE is the first Vietnamese language understanding evaluation benchmark launched by the University of Information Technology, Vietnam National University Ho Chi Minh City. It includes datasets for five distinct tasks, covering text classification, span extraction, natural language understanding and other related areas. These datasets vary in scale, data volume and token count, and are sourced from Vietnamese Wikipedia, social networks and articles. During its development, the research team carefully selected challenging yet solvable tasks to ensure the diversity and practicality of the datasets. VLUE aims to provide a standardized evaluation framework for the Vietnamese natural language processing (NLP) community, addressing the challenges of model evaluation and comparison, and advancing the development of Vietnamese language understanding technologies.