Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

NLP classification process flow.

More »

Fig 1 Expand

Fig 2.

Architecture of the CBOW model.

More »

Fig 2 Expand

Fig 3.

Architecture of the skip-gram model.

More »

Fig 3 Expand

Fig 4.

Architecture of the LSTM network.

More »

Fig 4 Expand

Fig 5.

The forget gate.

More »

Fig 5 Expand

Fig 6.

The input gate.

More »

Fig 6 Expand

Fig 7.

Updating the cell state.

More »

Fig 7 Expand

Fig 8.

The output gate.

More »

Fig 8 Expand

Fig 9.

Architecture of the BiLSTM model.

More »

Fig 9 Expand

Fig 10.

Structure of the fully connected layer.

More »

Fig 10 Expand

Table 1.

The experimental environment and software tools.

More »

Table 1 Expand

Fig 11.

Histogram of word counts.

More »

Fig 11 Expand

Fig 12.

Data processing flow of the proposed model.

More »

Fig 12 Expand

Table 2.

Table of configurable parameters.

More »

Table 2 Expand

Table 3.

Performance metrics.

More »

Table 3 Expand

Table 4.

Classification performance of the LSTM network.

More »

Table 4 Expand

Table 5.

Classification performance of the BiLSTM network.

More »

Table 5 Expand

Table 6.

Overall classification performance.

More »

Table 6 Expand

Fig 13.

Loss vs. epoch and accuracy vs. epoch on the training and validation sets.

More »

Fig 13 Expand

Fig 14.

Confusion matrices of the BiLSTM and LSTM networks.

More »

Fig 14 Expand

Table 7.

Classification performance of the model comparison experimental.

More »

Table 7 Expand

Fig 15.

Statistical chart of the results of the model comparison experiment.

More »

Fig 15 Expand