一个中国命名实体认可数据集,用于非物质文化遗产
Shiyun Long1,2, Wei Li3,4
1College of Computer Science, Sichuan Normal University, Chengdu, China.
Scientific data
|February 2, 2026
概括
本研究引入了一套新的中国数据集,用于在非物质文化遗产 (ICH) 中进行命名实体识别 (NER). 拟议的模型增强了用于数字保存和文化研究的知识提取.
科学领域:
- 自然语言处理自然语言处理.
- 数字人文学科 数字人文学科
- 文化遗产信息学 文化遗产信息学
背景情况:
- 命名实体识别 (NER) 对于在非物质文化遗产 (ICH) 中组织知识至关重要.
- 有限的注释数据集阻碍了ICH特定NER的进步.
- 现有的方法与文化遗产文本中复杂的语言模式作斗争.
研究的目的:
- 在ICH领域为NER开发一个专门的中国数据集.
- 为ICH知识提取量身定制的有效的NER模型提出建议.
- 促进对文化遗产的结构化知识表示和分析.
主要方法:
- 为ICH创建一个新的中国数据集,包括遗产项目,继承人和材料.
- 开发一种混合NER模型,将RoBERTa集成用于特征提取.
- 利用Kolmogorov-Arnold网络 (KAN) 来进行复杂的模式识别.
- 条件随机场 (CRF) 的应用用于强大的序列标记.
主要成果:
- 拟议的NER模型在识别和分类ICH实体方面表现出高度的有效性.
- 该模型成功地捕获了ICH文本中的复杂语义依赖关系.
- 实验结果验证了新数据集和拟议模型的实用性.
结论:
- 开发的数据集和NER模型显著提升了对非物质文化遗产的信息提取.
- 这项工作为数字保存,知识图表构建和文化研究提供了宝贵的资源.
- 这些发现为加强对文化遗产知识的结构化表现和分析铺平了道路.
相关概念视频
02:21Naming Enantiomers
26.0K
The naming of enantiomers employs the Cahn–Ingold–Prelog rules that involve assigning priorities to different substituent groups at a chiral center. Each enantiomer, being a distinct molecule, is assigned a unique name by the Cahn–Ingold–Prelog (CIP) rules, also called the R–S system. The prefix R- or S- attached to the chiral centers in an enantiomer is dependent on the spatial arrangement of the four substituents on the chiral center. The R–S system essentially comprises three...
26.0K
01:19Naming Skeletal Muscles
4.1K
The naming of the approximately 700 muscles in the human body is based on a set of criteria designed to provide descriptive information about each muscle, making it easier to identify and remember them.
The key factors used in naming muscles include:
The key factors used in naming muscles include:
4.1K
01:11Common Names of Aldehydes and Ketones
5.0K
Some common aldehydes and ketones are popularly known by their common names used historically and predate the IUPAC nomenclature.
Common names of aldehydes are derived from the names of their corresponding acid. For instance, the two-carbon aldehyde–acetaldehyde derives its name from the corresponding acid–acetic acid. Similarly, formaldehyde derives its name from formic acid and benzaldehyde from benzoic acid.
Aliphatic ketones are named by suffixing the word “ketone” to the...
Common names of aldehydes are derived from the names of their corresponding acid. For instance, the two-carbon aldehyde–acetaldehyde derives its name from the corresponding acid–acetic acid. Similarly, formaldehyde derives its name from formic acid and benzaldehyde from benzoic acid.
Aliphatic ketones are named by suffixing the word “ketone” to the...
5.0K
02:57Plant Tissue Culture
40.7K
Plant tissue culture is widely used in both primary and applied science. Applications range from plant development studies to functional gene studies, crop improvement, commercial micropropagation, virus elimination, and conservation of rare species.
40.7K
01:23The Role of Culture
419
Culture plays a crucial role in shaping self-identity and influencing thought and behavior, a foundational interest within social psychology. The multicultural perspective recognizes that individuals do not exist in a vacuum; instead, their experiences, perceptions, and actions are deeply influenced by the intersecting dimensions of their cultural, ethnic, and social group affiliations.Cultural Influence on Self-Identity and Social PerceptionCultural frameworks inform how individuals define...
419
01:26Self-Esteem and Culture
234
Self-esteem, a core psychological construct, is intricately shaped by cultural context and varies significantly between collectivist and individualistic societies. In collectivist cultures such as Japan, self-esteem tends to be flexible, context-sensitive, and influenced by relationships. A Japanese student, for instance, may show restraint in formal settings like school but behave more openly among close friends, reflecting the flexible and dynamic nature of self-concept in such...
234