CRF-GCN: An effective syntactic dependency model for aspect-level sentiment analysis

Huang, Bo; Zhang, Jiahao; Ju, Jiaji; Guo, Ruyan; Fujita, Hamido; Liu, Jin

doi:10.1016/j.knosys.2022.110125

Cited by 22 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Related Wordsmentioning

confidence: 99%

“…In terms of sentiment analysis, they are not only applicable to unimodal sentiment analysis (Zhang et al, 2022) but also to multimodal sentiment analysis (Firdaus et al, 2023). For example, Huang et al (2023) propose CRF-GCN, a model that utilizes conditional random fields (CRF) to extract opinion scopes of specific aspect words and (Bruna et al, 2014) in 2014, which imitates the characteristics of convolutional neural networks by superimposing multi-layer graph convolutions, and defines convolutional kernels and activation functions for each layer, and form graph convolutional neural networks. Due to its high spatiotemporal complexity, Defferrard subsequently proposed ChebNet (Defferrard et al, 2016) in 2016 to reduce the temporal complexity by using the Chebyshev polynomial as a convolutional kernel.…”

Section: Related Wordsmentioning

confidence: 99%

See 1 more Smart Citation

Dual-channel deep graph convolutional neural networks

Ye,

Li,

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

The dual-channel graph convolutional neural networks based on hybrid features jointly model the different features of networks, so that the features can learn each other and improve the performance of various subsequent machine learning tasks. However, current dual-channel graph convolutional neural networks are limited by the number of convolution layers, which hinders the performance improvement of the models. Graph convolutional neural networks superimpose multi-layer graph convolution operations, which would occur in smoothing phenomena, resulting in performance decreasing as the increasing number of graph convolutional layers. Inspired by the success of residual connections on convolutional neural networks, this paper applies residual connections to dual-channel graph convolutional neural networks, and increases the depth of dual-channel graph convolutional neural networks. Thus, a dual-channel deep graph convolutional neural network (D2GCN) is proposed, which can effectively avoid over-smoothing and improve model performance. D2GCN is verified on CiteSeer, DBLP, and SDBLP datasets, the results show that D2GCN performs better than the comparison algorithms used in node classification tasks.

show abstract

Section: Related Wordsmentioning

confidence: 99%

Section: Related Wordsmentioning

confidence: 99%

Dual-channel deep graph convolutional neural networks

Ye,

Li,

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Assuming that the sliding window size is w and the sliding window position is p, the matching function can be expressed as Eq. ( 1) [20].…”

Section: Structural Analysis Of Smoss Modelmentioning

confidence: 99%

Syntactic Analysis of SMOSS Model Combined with Improved LSTM Model: Taking English Writing Teaching as an Example

Yan

2023

Preprint

View full text Add to dashboard Cite

In order to improve learners' syntactic understanding and writing ability, thus effectively improving the quality of English writing teaching, this paper explores the method of combining Sequential Matching on Sliding Window Sequences (SMOSS) model with improved Long Short-Term Memory (LSTM) model in English writing teaching to improve the effect of syntactic analysis. Firstly, this paper analyzes the structure of SMOSS model. Secondly, this paper optimizes the traditional LSTM model by using Connectist Temporal Classification (CTC), and proposes an English text error detection model. Meanwhile, this paper combines the SMOSS model with the optimized LSTM model to form a comprehensive syntactic analysis framework, and designs and implements the structure and code of the framework. Finally, on the one hand, the semantic disambiguation performance of the model is tested by using SemCor data set. On the other hand, taking English writing teaching as an example, the proposed method is further verified by designing a comparative experiment in groups. The results show that: (1) From the experimental data of word sense disambiguation, the accuracy of the SMOSS-LSTM model proposed in this paper is the lowest when the context range is "3 + 3", then it rises in turn at "5 + 5" and "7 + 7", reaches the highest at "7 + 7", and then begins to decrease at "10 + 10"; (2) Compared with the control group, the accuracy of syntactic analysis in the experimental group reached 89.5%, while that in the control group was only 73.2%. (3) In the aspect of English text error detection, the detection accuracy of the proposed model in the experimental group is as high as 94.8%, which is significantly better than the traditional SMOSS-based text error detection method, and its accuracy is only 68.3%. This paper verifies the effectiveness and practicability of applying SMOSS model and improved LSTM model to the syntactic analysis task in English writing teaching, and provides new ideas and methods for the application of syntactic analysis in English teaching.

show abstract