Open Access

Pattern Recognition and Deep Semantic Network Analysis Techniques for Rhetorical Devices in English Literary Texts

Jianfu Tang

Jianfu Tang

School of Foreign Languages, Hunan University of Science and EngineeringYongzhou, China
Search for this author on
Sciendo|Google Scholar
Tang, Jianfu
  
Mar 19, 2025
Pattern Recognition and Deep Semantic Network Analysis Techniques for Rhetorical Devices in English Literary Texts's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Mar 19, 2025
Received: Oct 16, 2024
Accepted: Feb 09, 2025
DOI: https://doi.org/10.2478/amns-2025-0540
Keywords
© 2025 Jianfu Tang, published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Schematic diagram of pooling calculation
Schematic diagram of pooling calculation

Figure 2.

The impact of data size on downstream tasks
The impact of data size on downstream tasks

Figure 3.

The identification performance of different sentence lengths of the model
The identification performance of different sentence lengths of the model

Figure 4.

Model performance comparison of less samples
Model performance comparison of less samples

Figure 5.

Dependency parsing and part-of-speech tagging
Dependency parsing and part-of-speech tagging

Figure 6.

Synonymy network of evaluation objects
Synonymy network of evaluation objects

Figure 7.

LSTM storage block structure
LSTM storage block structure

Figure 8.

The vector distribution of six rhetorical relationships
The vector distribution of six rhetorical relationships

MPA_MTC and ATT-LSTM attention weight contrast

Serial number Target word Model Visual LSTM weight visualization Forecast Actual
(1) Gong yuan ATT-LSTM Gong yuan li de hua jing xiang kai fang. Positive Positive
Ours Gong yuan li de hua jing xiang kai fang. Positive
(2) Gong si ATT-LSTM Gong si jue ding yin ru yi tao guan li xi tong. Negativity Negativity
Ours Gong si jue ding yin ru yi tao guan li xi tong. Negativity
(3) Tian qi ATT-LSTM Jin tian tian qi zhen hao. Positive Negativity
Ours Jin tian tian qi zhen hao. Negativity
(4) Wo ATT-LSTM Wo kan le yi bu dian ying. Positive Negativity
Ours Wo kan le yi bu dian ying. Negativity

Different factors and the results of the experimental results

model Acc F1 (neg.) F1 (pos.) F1 (avg.)
LSTM 0.745 0.739 0.775 0.749
ATT-LSTM 0.754 0.737 0.76 0.756
TRAT-LSTM 0.766 0.768 0.773 0.77
MPA_MTC 0.776 0.778 0.776 0.773
Ours 0.795 0.784 0.794 0.789

Convolution neural network model parameters

Model layer name size Algorithm/method
Input layer 180*128 Longitudinal stack
Convolution layer 3*128,4*128,5*128 Relu activation function
Pooling layer 176*1,177*1,178*1 Max-Pooling
Full junction 128 The relu Dropout strategy

Example of LSTMweight value

Numbering LSTM weight
Gong si Jue ding Yin ru Yi tao Guan li xi tong.
(a) 0.067 0.063 0.053 0.031 0.045
(b) 0.361 0.049 0.495 0.035 0.052
(c) 0.52 0.067 0.297 0.043 0.055

The results of different models on CSR were compared to (%)

Model Precision Recall F1-score
SC 77.61 88.77 82.87
MTL-SC 80.77 92.09 86.3
Self_Attn+Pos 80.35 91.94 85.41
Cyc-MTL-SC 85.91 94.93 90.03
HGSR 89.29 94.79 91.68
Ours 91.24 91.22 90.73
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Life Sciences, Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics, Physics, other
Journal RSS Feed