Zelin Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zelin Guo has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Hai Huan
School of Artificial Intelligence Nanjing University of Information Science & Technology Nanjing China
1 shared publication- Hai Huan
School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China
1 shared publication Ruidong Zhang
School of Artificial Intelligence Nanjing University of Information Science & Technology Nanjing China
1 shared publication- Yaqin Xie
Nanjing University of Information Science and Technology
1 shared publication - Zichen He
School of Artificial Intelligence (School of Future Technology), Nanjing University of Information Science and Technology, Nanjing, China
1 shared publication
Latest Publications
- 21 November 2023
- Published by Wiley in Expert Systems
- Vol. 41 (3)
Text classification based on PEGCN: Graph convolution classification using location information and edge features
The purpose of text classification is to label the text with known labels. In recent years, the method based on graph neural network (GNN) has achieved good results. However, the existing methods based on GNN only regard the text as the set of co‐occurring words, without considering the position information of each word in the statement. At the same time, the method mainly extracts the node features in the graph, and the edge features between the nodes are not used enough. To solve these problems, a new text classification method, graph convolutional network using positions and edges, is proposed. In the word embedding section, a positional encoding input representation is employed to enable the neural network to learn the relative positional information among words. Meanwhile, the dimension of the adjacency matrix is increased to extract the multi‐dimensional edge features. Through experiments on multiple text classification datasets, the proposed method is shown to be superior to the traditional text classification method, and has achieved a maximum improvement of more than 4%.
- 21 November 2023
- Published by Wiley in Expert Systems
- Vol. 41 (3)
Text classification based on PEGCN: Graph convolution classification using location information and edge features
The purpose of text classification is to label the text with known labels. In recent years, the method based on graph neural network (GNN) has achieved good results. However, the existing methods based on GNN only regard the text as the set of co‐occurring words, without considering the position information of each word in the statement. At the same time, the method mainly extracts the node features in the graph, and the edge features between the nodes are not used enough. To solve these problems, a new text classification method, graph convolutional network using positions and edges, is proposed. In the word embedding section, a positional encoding input representation is employed to enable the neural network to learn the relative positional information among words. Meanwhile, the dimension of the adjacency matrix is increased to extract the multi‐dimensional edge features. Through experiments on multiple text classification datasets, the proposed method is shown to be superior to the traditional text classification method, and has achieved a maximum improvement of more than 4%.
- Open Access
- 26 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 103187-103199
A Multi-Task Dual-Encoder Framework for Aspect Sentiment Triplet Extraction
Aspect Sentiment Triplet Extraction (ASTE) is a complex and important task in aspect-based sentiment analysis task, which aims to extract aspect-sentiment-opinion triplets from review sentences, to acquire comprehensive information for sentiment analysis. Most of the existing methods use pipeline approaches or end-to-end sequence tagging approaches to solve the ASTE task. However, the pipeline approaches suffer from error accumulation in practical applications. The existing sequence tagging approaches ignore the feature information of the three elements themselves, and cannot model and infer the three elements effectively by placing each word in the same position as importance. Based on this, a multi-task dual-encoder framework is proposed. First, a dual-encoder is constructed to encode and fuse sentence information and semantic information, respectively. Then, the signs and constraints implied between word pairs are used to complete multi-task inference and triplet decoding. Meanwhile, two grid tagging methods and their corresponding inference strategies are designed for the multi-task. The auxiliary task is used as a regularization of the main task, which improves the correct inference ability of the inference strategy for the main task and the robustness of the framework. Extensive testing on two benchmark datasets shows that the proposed framework is simple and effective, and significantly outperforms the existing methods.
- 26 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 103187-103199
Open AccessA Multi-Task Dual-Encoder Framework for Aspect Sentiment Triplet Extraction
Aspect Sentiment Triplet Extraction (ASTE) is a complex and important task in aspect-based sentiment analysis task, which aims to extract aspect-sentiment-opinion triplets from review sentences, to acquire comprehensive information for sentiment analysis. Most of the existing methods use pipeline approaches or end-to-end sequence tagging approaches to solve the ASTE task. However, the pipeline approaches suffer from error accumulation in practical applications. The existing sequence tagging approaches ignore the feature information of the three elements themselves, and cannot model and infer the three elements effectively by placing each word in the same position as importance. Based on this, a multi-task dual-encoder framework is proposed. First, a dual-encoder is constructed to encode and fuse sentence information and semantic information, respectively. Then, the signs and constraints implied between word pairs are used to complete multi-task inference and triplet decoding. Meanwhile, two grid tagging methods and their corresponding inference strategies are designed for the multi-task. The auxiliary task is used as a regularization of the main task, which improves the correct inference ability of the inference strategy for the main task and the robustness of the framework. Extensive testing on two benchmark datasets shows that the proposed framework is simple and effective, and significantly outperforms the existing methods.