Graph convolutional networks with hierarchical multi-head attention for aspect-level sentiment classification

Li, Xiaowen; Lu, Ran; Liu, Peiyu; Zhu, Zhenfang

doi:10.1007/s11227-022-04480-w

Cited by 11 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu [14]extracted the semantic information between words in the specified aspect words by using multi-head attention and added SVM to replace the softmax function in the classification layer to obtain better sentiment features in high-dimensional space. Li [15]considers acquiring syntactic dependency information and combining semantic information to realize the interaction between aspect words and sentences by referring to attention-based graph convolutional neural (GCN) networks. Huang [16] designed a contextual location weighting function by considering the contextual location information of the aspect to reduce the interference of both sides of the aspect word on the sentiment polarity.…”

Section: A Aspect-level Sentiment Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Aspect-Level Sentiment Classification Based on Auto-Adaptive Model Transfer

et al. 2023

View full text Add to dashboard Cite

Aspect-level sentiment classification (ASC) is a fine-grained sentiment analysis task that involves detecting the sentiment polarity of a specific opinion target in a given sentence. Despite the popularity of deep learning methods, the limited availability of ASC training data has resulted in the suboptimal performance of neural network models. To address this issue, researchers have proposed transferring resource-rich document-level sentiment knowledge to ASC tasks using model transfer and shared parameters. However, these methods have neglected the impact of differences in the training data for different tasks on the shared layer parameters. Therefore, this paper proposes a transfer method that automatically adapts to task and domain differences-Auto-adaptive Model Transfer (AAMT). This method considers adding specific disturbance variables on shared layer parameters to subdivide task differences to further obtain more accurate and effective transfer knowledge. In addition, on this basis, we introduce an attention mechanism to combine aspect and sentence features to better capture the sentiment vocabulary associated with a given target. A series of experiments on three public datasets show that our proposed method can solve the problem of insufficient training data for ASC and achieve good results.

show abstract

Section: A Aspect-level Sentiment Classificationmentioning

confidence: 99%

“…𝑓(H 𝑖 , t) = H 𝑖 ⋅ W 𝑠 ⋅ t + b 𝑠 (15) Where 𝑒 𝑇 represents a column vector with all 1s, and t ⊗ 𝑒 𝑇 represents a continuous copy of the t vector 𝑇 times and concatenated.…”

Section: ) Attention Layermentioning

confidence: 99%

Aspect-Level Sentiment Classification Based on Auto-Adaptive Model Transfer

et al. 2023

View full text Add to dashboard Cite

show abstract

LoopNetica: Predicting Chromatin Loops Using Convolutional Neural Networks and Attention Mechanisms

Lei,

Tang,

Luo

et al. 2024

Bioinformatics Research and Applications

View full text Add to dashboard Cite

A multi-feature fusion approach based on domain adaptive pretraining for aspect-based sentiment analysis

Ma,

He,

Pang

et al. 2023

Soft Comput

View full text Add to dashboard Cite

Aspect-based sentiment classi cation (ASC) is a popular task that aims to identify the corresponding emotion of a speci c aspect for aspect-based sentiment analysis. Dependency parsing is currently considered as an e cient tool for recognizing the opinion words in the sentiment text. However, many dependency-based methods might be susceptible to the dependency tree and inevitably introduce noisy information and neglect the rich relation information between words. In this paper, we propose a multifeature fusion approach based on domain adaptive pretraining for ASC and reducing dependency noisy information. We use the Multi-task Learning (MTL) technique for domain adaptive pretraining, which combines Bia ne Attention Model (BAM) and Mask Language Model (MLM) by jointly considering the structure, relations of edges, and linguistic features in the sentiment text. The pretrained dependency graph will be input into a double graph fusion-based message passing neural network (MPNN) that is initialized with the optimal parameters of the pretrained BAM for MPNN training, which fully considers these different features that are affected with each other for ASC. Extensive experiments were made on four benchmark datasets for comparing our approach with the state-of-the-art ASC approaches, and the results show that our model is very competitive in the ASC task compared with the state-of-the-art alternatives.

show abstract

Graph convolutional networks with hierarchical multi-head attention for aspect-level sentiment classification

Cited by 11 publications

References 31 publications

Aspect-Level Sentiment Classification Based on Auto-Adaptive Model Transfer

Aspect-Level Sentiment Classification Based on Auto-Adaptive Model Transfer

LoopNetica: Predicting Chromatin Loops Using Convolutional Neural Networks and Attention Mechanisms

A multi-feature fusion approach based on domain adaptive pretraining for aspect-based sentiment analysis

Contact Info

Product

Resources

About