Abstract
At present, XBRL (Extensible Business Reporting Language) has been used in more and more countries and organizations. Although XBRL has achieved a series of remarkable achievements, the current development of XBRL has also encountered bottlenecks. On the one hand, the XBRL field has not been unified. On the other hand, the semantics of concepts in the domain ontology of XBRL is weak, resulting in the slow application and promotion of XBRL. This paper regulates the extraction of semantic primitives in the ontology of XBRL domain from the perspective of semantics and solves the problem of “how to extract semantic primitives”. The solution to this problem can promote computers to better understand XBRL financial reports and reduce the technical difficulty of XBRL. This paper comprehensively uses the theories of semantic primitives, graph theory, and domain ontology. First, it analyzes the research status and shortcomings of semantic primitive extraction methods. Second, it constructs a graph of accounting term relationship network from the perspective of graph theory. The extraction of semantic primitives. Finally, the validity of semantic primitive extraction is analyzed and verified.
Highlights
In the era of big data, information technology continues to develop, XBRL is used as a digital standard for business reporting
The extraction of semantic primitives is an important part of constructing the ontology in the field of XBRL, and its research has received widespread attention from scholars
Starting from the XBRL domain ontology, this paper analyzes the lexical features of the element list, which is an important corpus for constructing the XBRL domain ontology, and provides ideas and basis for the extraction of semantic primitives later
Summary
In the era of big data, information technology continues to develop, XBRL is used as a digital standard for business reporting. In order to realize the conversion of XBRL financial information, it is usually necessary to establish a mapping relationship between different classification standards. Domain ontology is a logical theory of terminology This term needs to be expressed with the help of a “core language”. In order to be able to construct the XBRL domain ontology more effectively, this paper applies semantic primitives to the field of financial reporting and builds a “core language” based on XBRL domain knowledge, which is an important foundation for the construction of domain ontology. How to extract semantic primitives to realize the construction of XBRL domain ontology is a scientific issue worthy of research. Based on the expression needs of the ontology in the XBRL domain, this paper uses the relevant corpus of the accounting field to construct a directed graph of accounting terms. The innovation of this article lies in: 1) Select an accounting dictionary that is more in line with domain knowledge as the data source; 2) Semantic primitives are linguistic concepts, which realize the expression of knowledge in the field of accounting with semantic primitives and realize cross-domain research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
