Hierarchical template transformer for fine-grained sentiment controllable generation

Li, Yuan; Wang, Jin; Yu, Liang-Chih; Zhang, Xuejie

doi:10.1016/j.ipm.2022.103048

Cited by 9 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aspect‐based sentiment analysis (ABSA) is a fine‐grained sentiment classification task, which is used to identify the sentiment polarity of a specific aspect in a sentence (Yuan et al, 2022). Liu et al (2023) proposed a DGGCN model based on contextual sentiment knowledge to enhance the impact of a given aspect on the context.…”

Section: Related Workmentioning

confidence: 99%

Linking negative herding effect to online public opinion: A new BiGADG approach for sentiment classification

Zhou,

Hu,

Liu

et al. 2024

Expert Systems

View full text Add to dashboard Cite

The negative herding effect tends to cause the spread of negative emotions among netizens, resulting in significant public opinion crises. Therefore, linking the negative herding effect and online public opinion, we aim to exploring the connection between netizens' emotions, opinions, and the negative herding effect. To better distinguish the emotions in texts, a new BiGADG (Bidirectional Gated recurrent unit based on Attention with Distance‐based dependency syntax Graph convolutional network) model is proposed in this article. This model includes primarily the proposed dependency syntax based on dependency distance, Bidirectional Gated Recurrent Unit (BiGRU), multi‐head self‐attention and Graph Convolutional Network (GCN). Particularly, the dependency syntax based on dependency distances incorporates word‐to‐word dependency distances into the traditional dependency syntax, which enriches the syntactic structural features of the text. After the experiments, the accuracy of BiGADG model is 86.53%, which is 3.11% higher compared to BERT model. It is evident that our model for sentiment classification has been improved. Based on the results of sentiment classification, we investigate the existence of negative herding behaviour and its underlying motivation in online public opinion. We have found that the negative herding effect, if not effectively managed, may trigger large‐scale and uncontrollable public opinion crises.

show abstract

Section: Related Workmentioning

confidence: 99%

Linking negative herding effect to online public opinion: A new BiGADG approach for sentiment classification

Zhou,

Hu,

Liu

et al. 2024

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Recently, there have been advancements in deep neural networks, which have proved to be powerful tools for image processing, disease diagnosis, natural language processing, and bioinformatics. [35][36][37][38][39][40][41][42][43][44][45][46] Each deep neural network employs different feature processing techniques and frameworks tailored to specific tasks. However, there is a bottleneck of deep learning-based models applied to predicting DNA-protein complex structures due to the limited number of available DNA-protein complex structures.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of DNA–protein complex structures using the deep learning method

Zeng,

Jian,

Zhuo

et al. 2024

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

show abstract

“…[2]. More specifically, thanks to advancements in the field of deep learning being applied in computer vision [3] and natural language processing [4,5], different proposals have been made to create artificial speech or sounds, with models such as recurrent neural networks [6], generative adversarial networks [7,8], variational autoencoders [9], and transformers [10]. One of the most recent and successful contributions in this field is the Jukebox [11,12].…”

Section: Introductionmentioning

confidence: 99%

Fast Jukebox: Accelerating Music Generation with Knowledge Distillation

2023

View full text Add to dashboard Cite

The Jukebox model can generate high-diversity music within a single system, which is achieved by using a hierarchical VQ-VAE architecture to compress audio in a discrete space at different compression levels. Even though the results are impressive, the inference stage is tremendously slow. To address this issue, we propose a Fast Jukebox, which uses different knowledge distillation strategies to reduce the number of parameters of the prior model for compressed space. Since the Jukebox has shown highly diverse audio generation capabilities, we used a simple compilation of songs for experimental purposes. Evaluation results obtained using emotional valence show that the proposed approach achieved a tendency towards actively pleasant, thus reducing inference time for all VQ-VAE levels without compromising quality.

show abstract

Hierarchical template transformer for fine-grained sentiment controllable generation

Cited by 9 publications

References 45 publications

Linking negative herding effect to online public opinion: A new BiGADG approach for sentiment classification

Linking negative herding effect to online public opinion: A new BiGADG approach for sentiment classification

Evaluation of DNA–protein complex structures using the deep learning method

Fast Jukebox: Accelerating Music Generation with Knowledge Distillation

Contact Info

Product

Resources

About