Ensemble application of bidirectional LSTM and GRU for aspect category detection with imbalanced data

Kumar, Jay; Abirami, S.

doi:10.1007/s00521-021-06100-9

Cited by 28 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that this experiment exceeded previous research conducted by [2]. The macro F1 and weighted average metrics determine model performance on unbalanced data [28]. Based on these scores, the "Treatment of Disease" class is interesting to analyse because it is always superior to the others on all metrics used, even though the amount of data is less than the "Negative" class.…”

Section: Performance Calculationmentioning

confidence: 74%

Plant-Disease Relation Model through BERT-BiLSTM-CRF Approach

Riyanto,

Sitanggang,

Djatna

et al. 2024

IJEEI

View full text Add to dashboard Cite

Plant Disease Relations (PDR) is one of the Information Extraction (IE) subtasks that reveals the relationship between plant entities and diseases that appear together in a sentence. Previous studies have proposed methods for detecting the extraction of relationships between plant diseases (PDR). Previous research has proposed a Short Dependency Path-Convolutional Neural Network (SDP-CNN) method to predict relationships. However, the proposed method has limitations when faced with long and complex sentences. To overcome these limitations, this study proposes the BERT-BiLSTM-CRF method to improve the model performance in detecting PDR. First, the data is processed into the BERT Encoder layer after the tokenization process. After the BERT Encoder calculates the hidden information, the next step is to enter the linear layer to obtain word embedding. Calculation results in the bilinear layer are forwarded to the softmax layer to predict the relationship of each pair. Computation results in the softmax layer are sent to the BiLSTM layer. Finally, the CRF layer is entered to improve the prediction process. An 80:20 ratio for training and testing data was used to build the model using the same parameter values over ten attempts. GridSearch hyperparameter tuning is also involved in improving model performance. Experimental results show that the architecture proposed in this research can increase the F1 score by 0.790, which proved to be higher than SDP-CNN with a micro F1 score of 0.764. The problem of predicting PDR was overcome by the BERT-BILSTM-CRF method. The issue of forecasting PDR was resolved using the BERT-BILSTM-CRF approach.

show abstract

Section: Performance Calculationmentioning

confidence: 74%

Plant-Disease Relation Model through BERT-BiLSTM-CRF Approach

Riyanto,

Sitanggang,

Djatna

et al. 2024

IJEEI

View full text Add to dashboard Cite

show abstract

“…Bidirectional LSTM is a modified structure based on LSTM by introducing positive and negative temporal directions. It has certain advantages in processing prediction based on time sequence, and can effectively avoid problems such as gradient disappearance or gradient explosion caused by time dependence [48]. Its structure is shown in figure 1(a).…”

Section: Bid-lstmmentioning

confidence: 99%

Fault diagnosis in asynchronous motors based on an optimal deep bidirectional long short-term memory networks

Xu,

Li,

Liu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Fault diagnosis of asynchronous motors has become a pressing need in the metallurgical industry. Due to the complex structure of asynchronous motors, fault types and fault characteristics are diverse, with strong nonlinear relationships between them, which leads to the difficulty of fault diagnosis. To efficiently and accurately diagnose various motor faults, we propose a fault diagnosis method based on an optimal deep bidirectional long short-term memory neural network. First, the three-phase current, multidimensional vibrational signal, and acoustic signal of the asynchronous motor are collected and construct diverse and robust data sample set to enhance the generalization ability of the model. Next, a modified 3D logistics-sine complex chaotic map (3D LSCCM) is constructed to improve the global and local search capabilities of the pigeon swarm optimization algorithm (PIO). Then, we construct a deep bidirectional long short-term memory network (Bid-LSTM) with attention mechanism to mine high-value fault characteristic information. Meanwhile, the optimal hyper-parameters of the deep ABid-LSTM are explored using the modified PIO to improve the training performance of the model. Finally, the fault data samples of asynchronous motor are induced to train and test the proposed framework. By fusing diverse data samples, the proposed method outperforms conventional deep Bid-LSTM and achieves fault diagnosis accuracy of 99.13%. It provides a novel diagnostic strategy for motor fault diagnosis.

show abstract

“…By adding aspect embedding to each word input vector, the model makes use of aspect information to help determine attention weight. [4] The imbalanced aspect category issue in deep neural networks is addressed in this research.…”

Section: Literature Surveymentioning

confidence: 99%

Survey on Aspect Based Sentimental Analysis using Deep Learning Techniques

Nandini¹,

Priya²,

Sruthi³

et al. 2023

Int. J. Res. Publ. Rev.

View full text Add to dashboard Cite

People People are increasingly using social media to communicate their views and ideas in daily life. Analysis, processing, interpretation, and inference of subjective texts with the sentiment are all steps in the sentiment analysis process. Businesses utilise sentiment analysis for a variety of purposes, including market research, brand reputation analysis, customer experience evaluation, and social media influence research. It can be classified into document, sentence, and aspect-based types in accordance with the various needs for aspect granularity. In order to determine the aspects of entities and the sentiment conveyed for each one, Aspect Based Sentimental Analysis (ABSA), a fine-grained task in sentiment analysis, is performed. Since it offers more thorough and detailed data, ABSA has drawn a lot of interest in recent years. Product dependence, target dependence, and aspect dependence are the three fundamental difficulties ABSA faces. In order to choose the best aspect extraction approach for the proposed model, we first compared the accuracy of two different methods, TF-IDF and PMI. The precise extraction technique is examined first with Bert and subsequently with various classifiers. The many classifiers are finally combined to produce a superior accuracy. Pretrained BERT that has been fine-tuned performs very well on ABSA. It makes use of BERT intermediate layers to improve the effectiveness of BERT finetuning. The suggested approach will be tested using two datasets, Amazon Unlocked Mobile and tripadvisor hotel reviews, where hotel reviews produce more accurate findings.

show abstract

Ensemble application of bidirectional LSTM and GRU for aspect category detection with imbalanced data

Cited by 28 publications

References 40 publications

Plant-Disease Relation Model through BERT-BiLSTM-CRF Approach

Plant-Disease Relation Model through BERT-BiLSTM-CRF Approach

Fault diagnosis in asynchronous motors based on an optimal deep bidirectional long short-term memory networks

Survey on Aspect Based Sentimental Analysis using Deep Learning Techniques

Contact Info

Product

Resources

About