Yanfeng Wang

Dr. Yanfeng Wang

avatar
Co-authors
avatar
Following
avatar
Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 October 2021
Verified
Conference Paper
Closed access
DZDengyun Zhu
Dengyun Zhu
YWYanfeng Wang
Yanfeng Wang
BWBin Wei
Bin Wei
ZGZechen Guo
Zechen Guo
FWFucheng Wan
Fucheng Wan
At present, we are in the era of big data. With the continuous development of the Internet, we are generating huge data that we cannot observe at any time. Traditional data analysis has been unable to meet the current needs, and the technology of data visualization can extract and analyze huge amounts of data, extract useful data and present them in the form of images or graphics. This article summarizes data visualization, and elaborates in detail through the introduction, the concept of visualization, the presentation of data in data visualization, and the current challenges.
3 September 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YWYanfeng Wang
Yanfeng Wang
NMNing Ma
Ning Ma
GZGuo ZeChen
Guo ZeChen
To address the problems of the insufficient semantic fusion between text and questions and the lack of consideration of global semantic information encountered in machine reading comprehension models, we proposed a machine reading comprehension model called BERT_hybrid based on the BERT and hybrid attention mechanism. In this model, BERT is utilized to separately map the text and questions into the feature space. Through the integration of Bi-LSTM, an attention mechanism, and a self-attention mechanism, the proposed model achieves a comprehensive semantic fusion between text and questions. The probability distribution of answers is computed using Softmax. The experimental results on the public dataset DuReader demonstrate that the proposed model achieves improvements in BLEU-4 and ROUGE-L scores compared to existing models. Furthermore, to validate the effectiveness of the proposed model design, we analyze the factors influencing the model’s performance.
31 January 2024
Verified
Book Chapter
Open access
PDF file
YWYanfeng Wang
Yanfeng Wang
Aiming at the problems of incomplete semantic understanding and insufficient word position information in complex Chinese word segmentation, a large-scale multilingual database Chinese word segmentation method based on hybrid deep learning technology is proposed. In this scheme, the bidirectional context information is effectively used through the bidirectional threshold circulation unit, and the long-distance dependency information is effectively modeled by the BiLSTM model. At the same time, the dependency between the output tags can be considered through the CRF layer. Then a double byte query method is proposed to expand the CRF model, and the whole process is realized by machine learning and training. The simulation results show that the hybrid model makes full use of the advantages that BiLSTM can extract local information by using long-distance information and CNN, and it can complete the task of Chinese word segmentation more efficiently and accurately. Under the same experimental conditions, the performance is improved by about 30% compared with similar methods.
14 May 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
YWYanfeng Wang
Yanfeng Wang
NMNing Ma
Ning Ma
GZGuo ZeChen
Guo ZeChen
To address the problems of insufficient semantic fusion between text and questions and the lack of consideration of global semantic information encountered in machine reading comprehension models, we proposed a machine reading comprehension model called BERT_hybrid based on BERT and hybrid attention mechanism. In this model, BERT is utilized to separately map the text and questions into the feature space. Through the integration of Bi-LSTM, attention mechanism, and self-attention mechanism, the proposed model achieves comprehensive semantic fusion between text and questions. The probabilities distribution of answers is computed using Softmax. Experimental results on the public dataset DuReader demonstrate that the proposed model achieves improvements in BLEU-4 and ROUGE-L scores compared to existing models. Furthermore, to validate the effectiveness of the proposed model design, we analyze the factors influencing the model’s performance.