Subjects: Library Science，Information Science >> Library Science submitted time 2023-07-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] From the perspective of knowledge topics, this paper try to solve the problems of overlaps and "information island" between courses in the existing curriculum system design and teaching by establishing a comprehensive curriculum knowledge system. Thus, the professional knowledge services can be carried out effectively.[Method/process] This study takes the main courses of clinical medicine as the research object, based on medical thesis vocabulary, electronic textbooks, electronic lesson plans and other medical education data, through the LDA model to deeply explore the knowledge topics in courses, and then using the correlation analysis method to reveal the fine-grained relationship between courses, knowledge topics and the courses and knowledge topics. Thus, a clinical medical course-knowledge topic graph is constructed.[Result/conclusion] The study constructs domain knowledge graph from the perspective of professional curriculum system and knowledge subject. The results will help teaching managers, teachers and students master the professional knowledge system, and carry out knowledge-oriented teaching activities. Furthermore, It can promote the development of knowledge organization and services in the medical field and the development of smart medical education.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] In order to further improve the effect of event extraction in the financial field, the correlation between the two subtasks of event extraction needs to be enhanced.[Method/process] This paper carried out related research about event extraction on Chinese financial texts,and proposed a joint extraction method of financial events that integrated the pre-training model and a multi-layer convolutional neural network. First, the pre-training model BERT captured the comprehensive semantic information of the sentence sequence, then accessed the multi-layer convolutional architecture designed in this paper——MultiCNN, hierarchically extracted local window and high-dimensional spatial semantic information, realized the two tasks of event recognition and element extraction at the same time, and then introduced contrast loss to further strengthen the association between the two tasks.[Result/conclusion] F1 has reached 82.20% on the Chinese financial event data set, which has a certain improvement over the benchmark extraction models.
Hits
Hits
Downloads
Comment