Understanding Gating Operations in Recurrent Neural Networks through Opinion Expression Extraction

Artificial neural networks (ANN) have attracted significant attention from researchers because many complex problems can be solved by training them. If enough data are provided during the training process, ANNs are capable of achieving good performance results. However, if training data are not enough, the predefined neural network model suffers from overfitting and underfitting problems. To solve these problems, several regularization techniques have been devised and widely applied to applications and data analysis. However, it is difficult for developers to choose the most suitable scheme for a developing application because there is no information regarding the performance of each scheme. This paper describes comparative research on regularization techniques by evaluating the training and validation errors in a deep neural network model, using a weather dataset. For comparisons, each algorithm was implemented using a recent neural network library of TensorFlow. The experiment results showed that an autoencoder had the worst performance among schemes. When the prediction accuracy was compared, data augmentation and the batch normalization scheme showed better performance than the others.

show abstract

“…Among them, the Gaussian noise control scheme is the most widely used. The scheme could be expressed using Equation (9) [45]:…”

Section: Applied Regularization Methods In the Experimentsmentioning

confidence: 99%

A Comparison of Regularization Techniques in Deep Neural Networks

Nusrat

Jang

2018

Symmetry

View full text Add to dashboard Cite

show abstract

“…In formulas (12) and (13), the number of markers for a certain element in each set is represented as | |.…”

Section: Evaluation Methodmentioning

confidence: 99%

“…Wang et al [12] use bidirectional long short-term memory (BiLSTM) to identify subjective expression elements and explored the internal mechanism of long shortterm memory (LSTM). It was found that LSTM has better adaptability to context than regular RNN.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Subjective Expressions Extracting Method for Social Opinion Mining

Yin

Wang

Chen

et al. 2020

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

Opinion mining plays an important role in public opinion monitoring, commodity evaluation, government governance, and other areas. One of the basic tasks of opinion mining is to extract the expression elements, which can be further divided into direct subjective expression and expressive subjective expression. For the task of subjective expression extraction, the methods based on neural network can learn features automatically without exhaustive feature engineering and have been proved to be efficient for opinion mining. Constructing adequate input vector which can encode sufficient information is a challenge of neural network-based approach. To cope with this problem, a novel representation method that combines the different features with word vectors is proposed. Then, we use neural network and conditional random field to train and predict the expressions and carry out comparative experiments on different methods and features combinations. Experimental results show the performance of the proposed model, and the F value outperforms other methods in comparative experimental dataset. Our work can provide hint for further research on opinion expression extraction.

show abstract

“…As a typical represent of hollow polyester fiber, Porel TM fiber becoming more and more attractive for clothing due to its advantages like moisture permeability, antistatic property, thermal retention, lightweight and so on [1][2]. Because the fabric must subject to mechanical force during dyeing, finishing and wearing processes, so mechanical property is one of the most important behaviors of textile fiber [3][4]. The main influence factors for fiber mechanical behavior are morphological structure, crystallinity and molecular orientation.…”

Section: Introductionmentioning

confidence: 99%

Effect of Thermal Finishing on the Mechanical Properties of Hollow Polyester Fiber

Wang

Yan

2014

AMR

View full text Add to dashboard Cite

The effect of thermal setting parameters namely tensile stress, temperature and time on the breaking strength and breaking elongation of hollow polyester (PET) fiber (PorelTM fiber) were investigated, and their synergistic effect was studied via orthogonal experiment. The results show that protection of fiber wall is an important task during thermal finishing process of hollow fiber. There are direct relationships between micro-molecular structure and mechanical properties. Orthogonal experiment analysis shows that the most significant effect factor for breaking strength and breaking elongation are temperature and tensile stress, respectively. The suggested thermal finishing conditions for PorelTM fiber are summarized as following: elongation (viz. tensile stress) 4%, temperature 165°C, and time 60s.

show abstract

Understanding Gating Operations in Recurrent Neural Networks through Opinion Expression Extraction

Cited by 3 publications

References 17 publications

A Comparison of Regularization Techniques in Deep Neural Networks

A Comparison of Regularization Techniques in Deep Neural Networks

A Subjective Expressions Extracting Method for Social Opinion Mining

Effect of Thermal Finishing on the Mechanical Properties of Hollow Polyester Fiber

Contact Info

Product

Resources

About