Gated dynamic convolutions with deep layer fusion for abstractive document summarization

Kwon, Heock-Hoi; Go, Byung-Hyun; Park, Juhong; Lee, WonKee; Jeong, Yewon; Lee, Jong-Hyeok

doi:10.1016/j.csl.2020.101159

Cited by 7 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this process, it is analyzed and processed until it reaches the output layer and the final output result. Forward propagation refers to this output process [14]. Once the forward propagation is over, the output results will be compared with the data accuracy, and the network state will be evaluated in the form of error comparison.…”

Section: Deep Convolution Neural Network Training Algorithmmentioning

confidence: 99%

Application of Internet of Things Technology in Optimization of Electronic Assembly Process Parameters

Song¹

2022

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

In order to meet the demand of the Internet of things in the intelligent power monitoring system, this paper proposes a method to build an intelligent power monitoring system by combining 4G technology, the Android operating system, and other technologies closely related to the Internet of things. This method is evaluated by building an intelligent monitoring system and a transit node system and observing the test speed in the coco data set and the Pascal VOC data set. The experimental results show that the accuracy of animals measured by this method can reach up to 81%; the accuracy of humans can reach up to 76%; and the accuracy of vehicles can reach up to 87%. Conclusion. The application of Internet of things technology in the optimization of electronic assembly process parameters can quickly and effectively reflect the information in practical applications, so as to achieve the goal of seamless link and information exchange between things and people, and accurately manage and control the physical world in real time on the basis of scientific decisions.

show abstract

Section: Deep Convolution Neural Network Training Algorithmmentioning

confidence: 99%

Application of Internet of Things Technology in Optimization of Electronic Assembly Process Parameters

Song¹

2022

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

show abstract

“…In formula (14), C zc represents the calculated difference, A α and B β represent the adjustable parameters of reconstructed pixels, and O p represents the output pixel function. According to the calculated difference value, same detail parameters are set in the guidance area, and the numerical relationship of the set parameters can be expressed as:…”

Section: Construction Of Region Hierarchical Enhancement Methods For ...mentioning

confidence: 99%

“…The specific operation process is as follows: segment the whole fuzzy defect image, divide it into small blocks, and transmit it to the depth generation network by batch. The depth generation network contains 16 convolution layers, which can realize the output of residual blocks as demonstrated [14]. It is accumulated with the transmitted fuzzy defect image block to obtain the recovered image block, which is transmitted to the discrimination network together with the real image block.…”

Section: Fuzzy Defect Image Restoration Based On Neural Networkmentioning

confidence: 99%

Restoration and Enhancement of Fuzzy Defect Image Based on Neural Network

Zhan-Peng Cui

2023

Journal of Computers

View full text Add to dashboard Cite

<p>In contrast enhancement of fuzzy defect image, details loss and noise expansion are east to occur, which brings difficulties to subsequent image analysis and defect recognition. Therefore, a fuzzy defect image restoration and enhancement method based on neural network is proposed. A double fusion neural network composed of a depth generation network and a discrimination network is designed. The residual of the denoised fuzzy image and the real image is output by the network, which is input into the discrimination network together with the real image, and the difference between the two is judged by the total loss function. To solve the problem of pixel coordinate value of fuzzy defect image, neural network is used to build a fast correction algorithm. Therefore, a fuzzy image restoration and enhancement method based on neural network is proposed to improve the image quality. By reconstructing the resolution of fuzzy defect image, a hierarchical enhancement method of fuzzy defect image region is constructed to achieve fuzzy defect image restoration and enhancement. The results show that the proposed method has high image processing ability in restoration and enhancement of fuzzy defect images. The fitting value of neural network is 0.92, which is significantly higher than that of the other two methods, indicating that the image restoration and enhancement method based on neural network has higher accuracy. Therefore, the restoration and enhancement method of fuzzy defect image based on neural network has a good restoration and enhancement effect, and can effectively meet the actual needs of people for high-quality images.</p> <p> </p>

show abstract

“…Ortholy-linear combinations have been designed to maximize features in the linear combination of explicative variables. There are two basic stages of Fuzzy ELM (F-ELM), [29] called preparation and prediction. P. Verma and H. Om [30] proposed the Correlation-based Feature Selection (CFS) method.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid Ensemble Word Embedding based Classification Model for Multi-document Summarization Process on Large Multi-domain Document Sets

Devi¹,

Sivakumar²

2021

IJACSA

View full text Add to dashboard Cite

Contextual text feature extraction and classification play a vital role in the multi-document summarization process. Natural language processing (NLP) is one of the essential text mining tools which is used to preprocess and analyze the large document sets. Most of the conventional single document feature extraction measures are independent of contextual relationships among the different contextual feature sets for the document categorization process. Also, these conventional word embedding models such as TF-ID, ITF-ID and Glove are difficult to integrate into the multi-domain feature extraction and classification process due to a high misclassification rate and large candidate sets. To address these concerns, an advanced multi-document summarization framework was developed and tested on number of large training datasets. In this work, a hybrid multi-domain glove word embedding model, multi-document clustering and classification model were implemented to improve the multi-document summarization process for multi-domain document sets.Experimental results prove that the proposed multi-document summarization approach has improved efficiency in terms of accuracy, precision, recall, F-score and run time (ms) than the existing models.

show abstract

Gated dynamic convolutions with deep layer fusion for abstractive document summarization

Cited by 7 publications

References 1 publication

Application of Internet of Things Technology in Optimization of Electronic Assembly Process Parameters

Application of Internet of Things Technology in Optimization of Electronic Assembly Process Parameters

Restoration and Enhancement of Fuzzy Defect Image Based on Neural Network

A Hybrid Ensemble Word Embedding based Classification Model for Multi-document Summarization Process on Large Multi-domain Document Sets

Contact Info

Product

Resources

About