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

Zhang, Chengzhi; Mayr, Philipp; Lu, Wei; Zhang, Yi

doi:10.1108/ajim-05-2023-507

Cited by 11 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, previous works on the extraction of named entities from acknowledgements texts were mostly concerned with the extraction of funding information, i.e., only names of funding bodies and grant numbers, or extraction and linking of individuals. The special issue by Zhang et al (2023) provided a recent overview of current works in the extraction of knowledge entities.…”

Section: Ner In Scientometrics Analysismentioning

confidence: 99%

Embedding models for supervised automatic extraction and classification of named entities in scientific acknowledgements

Smirnova,

Mayr

2023

Scientometrics

Self Cite

View full text Add to dashboard Cite

Acknowledgments in scientific papers may give an insight into aspects of the scientific community, such as reward systems, collaboration patterns, and hidden research trends. The aim of the paper is to evaluate the performance of different embedding models for the task of automatic extraction and classification of acknowledged entities from the acknowledgment text in scientific papers. We trained and implemented a named entity recognition (NER) task using the flair NLP framework. The training was conducted using three default Flair NER models with four differently-sized corpora and different versions of the flair NLP framework. The Flair Embeddings model trained on the medium corpus with the latest FLAIR version showed the best accuracy of 0.79. Expanding the size of a training corpus from very small to medium size massively increased the accuracy of all training algorithms, but further expansion of the training corpus did not bring further improvement. Moreover, the performance of the model slightly deteriorated. Our model is able to recognize six entity types: funding agency, grant number, individuals, university, corporation, and miscellaneous. The model works more precisely for some entity types than for others; thus, individuals and grant numbers showed a very good F1-Score over 0.9. Most of the previous works on acknowledgment analysis were limited by the manual evaluation of data and therefore by the amount of processed data. This model can be applied for the comprehensive analysis of acknowledgment texts and may potentially make a great contribution to the field of automated acknowledgment analysis.

show abstract

Section: Ner In Scientometrics Analysismentioning

confidence: 99%

Embedding models for supervised automatic extraction and classification of named entities in scientific acknowledgements

Smirnova,

Mayr

2023

Scientometrics

Self Cite

View full text Add to dashboard Cite

show abstract

Prefabricated Building Model Construction Using Artificial Intelligence Algorithms

Ran,

Han

2024

Novel Technology and Whole-Process Management in Prefabricated Building

View full text Add to dashboard Cite

Artificial intelligence has become a hot research topic in the field of technology worldwide today. This article will discuss a hash and genetic algorithm based model suitable for prefabricated buildings. This article first introduces the application of artificial intelligence algorithms in solving nonlinear programming problems. Then this article proposes to improve the time loss caused by vector distortion caused by similar neighborhood selection in traditional methods, and preprocess the results to improve decision-making accuracy and other characteristics. Finally, this article verifies through experiments that the model is more effective and operable than traditional algorithms under the optimization of artificial intelligence algorithms. The verification results are as follows: In terms of running speed, the performance of artificial intelligence algorithms is 43 m/s, while the performance of traditional algorithms is 24 m/s; In terms of operational efficiency, the performance result of artificial intelligence algorithms is 95%, while the performance effect of traditional algorithms is 74%; In terms of visualization level, artificial intelligence algorithms have higher performance results, while traditional algorithms have lower performance effects. In terms of reliability, the performance result of artificial intelligence algorithms is 0.53, while the performance score of traditional algorithms is 0.43; In terms of robustness, the performance of artificial intelligence algorithms is 0.74, while the performance result of traditional algorithms is 0.67. The accuracy of artificial intelligence algorithms is 84%, while the accuracy of traditional algorithms is 65%. These test results indicate that using artificial intelligence algorithms can assist designers and engineers in optimizing design, automatically generating models, and conducting structural analysis and durability verification. This method helps to reduce errors and waste in the construction process, improve building quality and construction speed.

show abstract

2SCE-4SL: a 2-stage causality extraction framework for scientific literature

Zhang,

Bai,

Kong

et al. 2023

Scientometrics

View full text Add to dashboard Cite

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

Cited by 11 publications

References 18 publications

Embedding models for supervised automatic extraction and classification of named entities in scientific acknowledgements

Embedding models for supervised automatic extraction and classification of named entities in scientific acknowledgements

Prefabricated Building Model Construction Using Artificial Intelligence Algorithms

2SCE-4SL: a 2-stage causality extraction framework for scientific literature

Contact Info

Product

Resources

About