download174 view760
twitter facebook

공공누리This item is licensed Korea Open Government License

Title
Automatic Linkage Model of Classification Systems Based on a Pretraining Language Model for Interconnecting Science and Technology with Job Information
Author(s)
Jeong, Hyun JiJang, GwangseonShin, DongguKim, Tae Hyun
Publisher
Korea Institute of Science and Technology Information
Publication Year
2022-06-20
Abstract
For national industrial development in the Fourth Industrial Revolution, it is necessary to provide researchers with appropriate job information. This can be achieved by interconnecting the National Science and Technology Standard Classification System used for management of research activity with the Korean Employment Classification of Occupations used for job information management. In the present study, an automatic linkage model of classification systems is introduced based on a pre-trained language model for interconnecting science and technology information with job information. We propose for the first time an automatic model for linkage of classification systems. Our model effectively maps similar classes between the National Science & Technology Standard Classification System and Korean Employment Classification of Occupations. Moreover, the model increases interconnection performance by considering hierarchical features of classification systems. Experimental results show that precision and recall of the proposed model are about 0.82 and 0.84, respectively.
Keyword
linkage of classification systems; text analysis; pre-trained language model; Bidirectional Encoder Representations from Transformers
Journal Title
Journal of Information Science Theory and Practice;Volume 10 Special Issue
ISSN
2287-4577
DOI
https://doi.org/10.1633/JISTaP.2022.10.S.4
Files in This Item:
Thumbnail Automatic Linkage Model of Classification Systems Based on a Pretraining Language Model for Interconnecting Science and Technology with Job Information.pdf312.38 kBDownload
Appears in Collections:
8. KISTI 간행물 > JISTaP > Vol. 10 - Special Issue
Type
Serial
URI
https://repository.kisti.re.kr/handle/10580/18123
Export
RIS (EndNote)
XLS (Excel)
XML

Browse