ABSTRACT
At present, most enterprises and organizations attach great importance to the establishment of knowledge base in order to condense and summarize their core competitiveness, so as to inherit knowledge. However, at present, most of the knowledge base is a document library, and the structured information in the knowledge base is very lacking. Based on this, this paper proposes a knowledge embedding vector technology, which combines keyword extraction and text self-coding technology, so as to abstract and represent knowledge semantically in embedded vector space, and achieve the purpose of enriching structured information in knowledge base. Moreover, the knowledge embedding vector technology proposed in this paper can provide theoretical basis for the upper application of knowledge base, such as knowledge graph construction, knowledge search, knowledge recommendation and application.
- Ling Tian; Xue Zhou; Yan-Ping Wu; Wang-Tao Zhou; Jin-Hao Zhang; Tian-Shu Zhang. Knowledge Graph and Knowledge Reasoning: A Systematic Review [J]. Journal of Electronic Science and Technology, 2022, (02).Google Scholar
- Rafail Promikyridis [1]; Efthimios Tambouris [1].Using Knowledge Graphs to provide public service information [C].dg.o: Digital Government Research.dg.o 2022: DG.O 2022: The 23rd Annual International Conference on Digital Government Research: Association for Computing Machinery, 2022: 252–259.Google Scholar
- Paulus, A; Burgdorf, A; Stephan, A; Pomp, A; Meisen, T. Using Node Embeddings to Generate Recommendations for Semantic Model Creation [C]. 2022: 10.Google Scholar
- Liang Xiao, 1 Nianmin Yao2. Research on Chinese classification based on TF-IDF [C]. Society of Photo-Optical Instrumentation Engineers Proceedings (SPIE Proceedings), 2021.Google Scholar
- Fang Du [1]; Jiangshe Zhang [1]; Nannan Ji [2]; Junying Hu [1]; Chunxia Zhang [1].Discriminative Representation Learning with Supervised Auto-encoder[J]. Neural Processing Letters, 2019, 49 (2): 507-520.Google ScholarDigital Library
- Li, Yingying (1); Shen, Bo (1). Research on sentiment analysis of microblogging based on LSA and TF-IDF[C]. 2018, 2018-January.Google Scholar
- Wendland, André [1]; Zenere, Marco [2]; Niemann, Jörg [3].Introduction to Text Classification: Impact of Stemming and Comparing TF-IDF and Count Vectorization as Feature Extraction Technique [C]. 2021, 1442.Google Scholar
- KENNETH WARD CHURCH.Word2Vec [J]. Natural Language Engineering, 2017, 23 (01): 155-162.Google ScholarCross Ref
- Yushang Mao [1]; Guixuan Zhang [2]; Shuwu Zhang [3].Word Semantic Similarity Based on CiLin and Word2vec [C]. 2020 International Conference on Culture-oriented Science & Technology (ICCST). Culture-oriented Science & Technology (ICCST), International Conference on: 2020.Google Scholar
- Si-si Zhang [1]; Jian-wei Liu [1]; Xin Zuo [1]; Run-kun Lu [1]; Si-ming Lian [1].Online deep learning based on auto-encoder [J]. Applied Intelligence, 2021, 51 (8): 5420-5439.Google ScholarDigital Library
Index Terms
- Research on the knowledge embedding vector method based on TF-IDF and Auto-Encoder
Recommendations
Research on Knowledge Model for Ontology-Based Knowledge Base
BCGIN '11: Proceedings of the 2011 International Conference on Business Computing and Global InformatizationThe robust knowledge base needs a reasonable design pattern to represent knowledge model. On the foundation of the research about relationship of knowledge model with knowledge ontology, the knowledge model defined by three categories of domain ...
Research of the Tacit Knowledge Management on the Knowledge Intensity Enterprise
FITME '08: Proceedings of the 2008 International Seminar on Future Information Technology and Management EngineeringThe knowledge has already become an important fountainhead to arise the enterprise’s competitive ability in the period of knowledge economy. The knowledge management plays an important role in the management of the enterprise. The tacit knowledge is the ...
Knowledge based Least Squares Twin support vector machines
We propose knowledge based versions of a relatively new family of SVM algorithms based on two non-parallel hyperplanes. Specifically, we consider prior knowledge in the form of multiple polyhedral sets and incorporate the same into the formulation of ...
Comments