Distant Supervised Relation Extraction via DiSAN-2CNN on a Feature Level

Lv, Xueqiang; Hou, Huixin; You, Xindong; Zhang, Xiaopeng; Han, Junmei

doi:10.4018/ijswis.2020040101

Cited by 8 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Certain watermark data is used while training the model which helps the system to effectively detect and extract the watermark signal. Lv et al [ 13 ] present a novel application of CNN for Relation extraction which is one of the most important tasks in Natural Language Processing (NLP). Authors have utilized both CNN and directional self-attention network (DiSAN) model where pooling layers of CNN are modified to reduce the dimensions of the feature vector.…”

Section: Introductionmentioning

confidence: 99%

C-COVIDNet: A CNN Model for COVID-19 Detection Using Image Processing

et al. 2022

View full text Add to dashboard Cite

COVID-19 has become a global disaster that has disturbed the socioeconomic fabric of the world. Efficient and cost-effective diagnosis methods are very much required for better treatment and eliminating false cases for COVID-19. COVID-19 disease is a type of respiratory syndrome, thus lung X-ray analysis has got the attention for an effective diagnosis. Hence, the proposed study introduces an Image processing based COVID-19 detection model C-COVIDNet, which is trained on a dataset of chest X-ray images belonging to three categories: COVID-19, Pneumonia, and Normal person. Image preprocessing pipeline is used for extracting the region of interest (ROI), so that the required features may be present in the input. This lightweight convolution neural network (CNN) based approach has achieved an accuracy of 97.5% and an F1-score of 97.91%. Model input images are generated in batches using a custom data generator. The performance of C-COVIDNet has outperformed the state-of-the-art. The promising results will surely help in accelerating the development of deep learning-based COVID-19 diagnosis tools using radiography.

show abstract

Section: Introductionmentioning

confidence: 99%

C-COVIDNet: A CNN Model for COVID-19 Detection Using Image Processing

et al. 2022

View full text Add to dashboard Cite

show abstract

“…There is room for improvement in the overall accuracy of the prediction model, particularly in terms of increasing the time of in-advance prediction. Suggested future research directions include (i) increasing the number of data points used through data generation and augmentation techniques [ 58 , 59 ]; (ii) incorporating deep learning to extract features from the input data [ 60 , 61 ]; (iii) investigating the enhancement of algorithms through boosting techniques such as multiple RNNs, multiple GRUs, and multiple LSTMs [ 62 , 63 ]; and (iv) investigating the transition between classes.…”

Section: Discussionmentioning

confidence: 99%

Extended-Range Prediction Model Using NSGA-III Optimized RNN-GRU-LSTM for Driver Stress and Drowsiness

Chui¹,

Gupta

Liu

et al. 2021

Sensors

View full text Add to dashboard Cite

Road traffic accidents have been listed in the top 10 global causes of death for many decades. Traditional measures such as education and legislation have contributed to limited improvements in terms of reducing accidents due to people driving in undesirable statuses, such as when suffering from stress or drowsiness. Attention is drawn to predicting drivers’ future status so that precautions can be taken in advance as effective preventative measures. Common prediction algorithms include recurrent neural networks (RNNs), gated recurrent units (GRUs), and long short-term memory (LSTM) networks. To benefit from the advantages of each algorithm, nondominated sorting genetic algorithm-III (NSGA-III) can be applied to merge the three algorithms. This is named NSGA-III-optimized RNN-GRU-LSTM. An analysis can be made to compare the proposed prediction algorithm with the individual RNN, GRU, and LSTM algorithms. Our proposed model improves the overall accuracy by 11.2–13.6% and 10.2–12.2% in driver stress prediction and driver drowsiness prediction, respectively. Likewise, it improves the overall accuracy by 6.9–12.7% and 6.9–8.9%, respectively, compared with boosting learning with multiple RNNs, multiple GRUs, and multiple LSTMs algorithms. Compared with existing works, this proposal offers to enhance performance by taking some key factors into account—namely, using a real-world driving dataset, a greater sample size, hybrid algorithms, and cross-validation. Future research directions have been suggested for further exploration and performance enhancement.

show abstract

“…Srinivasan and L D, (2019) proposed a twofold convolutional neural network approach with a new activation function, which generalizes faster with higher accuracy. Lv et al (2020) proposed a distant supervised relation extraction model , in which a multidimension self-attention mechanism is utilized to encode the features of the words together with the entire sentence. Siriwon Taewijit, & Thanaruk Theeramunkong (2021) found that DL can be very helpful for diagnosing neurological disorders by its symptoms, because DL can be used to identify patterns for each disorder for identification.…”

Section: Pipeline Methodsmentioning

confidence: 99%

“…Most joint entity-relationship extractions are still supervised learning approaches that require a large amount of high-quality training set (Lv et al, 2020). Recent research tried to deal with the problem of having a relatively small training sample size.…”

Section: Joint Methodsmentioning

confidence: 99%

Fine-Grained Drug Interaction Extraction Based on Entity Pair Calibration and Pre-Training Model for Chinese Drug Instructions

Zhang

Gao

Zhou

et al. 2022

International Journal on Semantic Web and Information Systems

View full text Add to dashboard Cite

Existing pharmaceutical information extraction research often focus on standalone entity or relationship identification tasks over drug instructions. There is a lack of a holistic solution for drug knowledge extraction. Moreover, current methods perform poorly in extracting fine-grained interaction relations from drug instructions. To solve these problems, this paper proposes an information extraction framework for drug instructions. The framework proposes deep learning models with fine-tuned pre-training models for entity recognition and relation extraction, in addition, it incorporates an novel entity pair calibration process to promote the performance for fine-grained relation extraction. The framework experiments on more than 60k Chinese drug description sentences from 4000 drug instructions. Empirical results show that the framework can successfully identify drug related entities (F1 ≥ 0.95) and their relations (F1 ≥ 0.83) from the realistic dataset, and the entity pair calibration plays an important role (~5% F1 score improvement) in extracting fine-grained relations.

show abstract

Distant Supervised Relation Extraction via DiSAN-2CNN on a Feature Level

Cited by 8 publications

References 14 publications

C-COVIDNet: A CNN Model for COVID-19 Detection Using Image Processing

C-COVIDNet: A CNN Model for COVID-19 Detection Using Image Processing

Extended-Range Prediction Model Using NSGA-III Optimized RNN-GRU-LSTM for Driver Stress and Drowsiness

Fine-Grained Drug Interaction Extraction Based on Entity Pair Calibration and Pre-Training Model for Chinese Drug Instructions

Contact Info

Product

Resources

About