Extracting entity relations for “problem-solving” knowledge graph of scientific domains using word analogy

Chen, Guo; Peng, Jiabin; Xu, Tianxiang; Xiao, Lu

doi:10.1108/ajim-03-2022-0129

Cited by 8 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…“Problem-solving” stands out as one of the most fundamental and critical insights of scientific research. Using computer vision as an example, Chen et al . (2023) built a “problem-solving” knowledge graph of scientific domains by extracting four entity relation types, namely problem-solving, problem hierarchy, solution hierarchy and association.…”

Section: Topics In This Special Issuementioning

confidence: 99%

Guest editorial: Extraction and evaluation of knowledge entities in the age of artificial intelligence

Zhang

Mayr

et al. 2023

AJIM

View full text Add to dashboard Cite

Section: Topics In This Special Issuementioning

confidence: 99%

Guest editorial: Extraction and evaluation of knowledge entities in the age of artificial intelligence

Zhang

Mayr

et al. 2023

AJIM

View full text Add to dashboard Cite

“…Knowledge representation learning is the basis for cognitive graph construction [14][15]. In cognitive graphs, facts are stored in the form of directed graphs, in which entities are represented as nodes and relationships between entities are represented as edges, i.e., in the form of ternary groups.…”

Section: Knowledge Representation Learningmentioning

confidence: 99%

A Study of Minority Culture Outreach Translation Based on Cognitive Mapping Construction

Jin

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In this paper, we first construct a cognitive neural network and use the knowledge representation learning technique for knowledge complementation and relation extraction to semantically match head-tail entity pairs with relations and accurately model the semantic relationships between entities and relations. Then, the vectors of each entity are mapped onto the hyperplane of a given relation by the cognitive mapping translation model, and vector translation operations are performed on the hyperplane. Finally, this paper’s translation model is compared with other models to compare the semantic representation translation, task processing function, and model complexity of each model so as to verify the superiority of this paper’s model for minority culture outreach translation. The results show that this paper’s method increases 3.4 and 1.2 BLEU values on average in the four translation tasks compared to the Imagination model and VAG model, respectively. When the number of iterations is 40, the MRR value of this paper’s model is 0.345, which is at least 0.1-0.5 more than the other models, thus indicating that this paper’s model has a better performance in outreach translation.

show abstract

“…Knowledge graph is a large-scale semantic network, rich in concepts, entities, and various semantic relationships, and is currently the fastest-growing and most widely used tool for knowledge expression and information processing. Literature [21] uses computer vision as a case study to demonstrate the application of extracted relationships in constructing domain knowledge graphs and revealing historical research trends. A method that is both highly efficient and generalized is used.…”

Section: Introductionmentioning

confidence: 99%

Construction of Knowledge Mapping of College Students’ Civic and Political Informatization Education in Colleges and Universities

Zheng

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper combines the knowledge related to the Knowledge Graph to store and manage the ideological knowledge in the schema layer in the form of an ontology repository. The Bootstrapping-based extraction method has been improved for entity relationship extraction at the data layer, and semantically constrained relationships have been added to reduce the problem of extraction bias. Civics education’s characteristic attributes are identified through attribute extraction using crowdsourcing. For the entity alignment problem in entity extraction, the relationship triad and attribute triad are jointly used for entity vector characterization, and the entity alignment model based on BERT and TransE is proposed. Finally, in the process of testing knowledge mapping, more than 70% of college students were satisfied, and the percentage of college students agreeing and strongly agreeing in the dimensions of knowledge construction were 68.81%, 77.92%, and 75.63%, respectively. In the six dimensions of positive psychological quality of college students who have used knowledge mapping, there is a significant increase in the data of the courage dimension from 3.4 to 4.14, and the other dimensions have also increased. The performance of the knowledge graph constructed in this paper for civic information education is outstanding.

show abstract

Extracting entity relations for “problem-solving” knowledge graph of scientific domains using word analogy

Cited by 8 publications

References 41 publications

Guest editorial: Extraction and evaluation of knowledge entities in the age of artificial intelligence

Guest editorial: Extraction and evaluation of knowledge entities in the age of artificial intelligence

A Study of Minority Culture Outreach Translation Based on Cognitive Mapping Construction

Construction of Knowledge Mapping of College Students’ Civic and Political Informatization Education in Colleges and Universities

Contact Info

Product

Resources

About