Search

Abstract Aspect-based sentiment analysis (ABSA) is a challenging task due to the presence of multiple aspect words with different sentiment polarities in a sentence. Recently, pre-trained language models like BERT have been widely used as context encoders in ABSA. Graph neural networks have also been employed to extract syntactic and semantic information from sentence parsing trees, resulting in superior results. However, dependency trees may establish irrelevant dependencies for sentences with irregular syntax and complex structures. Additionally, previous methods have not fully utilized recent developments in pre-trained language models. Therefore, we propose a Dual Syntax aware Graph attention networks with Prompt (DSGP) model to address these issues. Our model utilizes prompt templates to maximize the potential of pre-trained models and masked vector outputs of templates as supplementary aspect feature representations. We also leverage both dependency trees and constituent trees with graph attention networks to extract different types of syntactic information. The dependency tree captures syntactic correlation between words, while the constituent tree provides a high-level formation of the sentence. Finally, the output from the prompt and parsing trees is fused and fed into a standard classifier. Experimental results on four public datasets demonstrate the competitive performance of our model.

Abstract Fructose consumption induces metabolic syndrome to increase cardiovascular disease risk. Cinnamaldehyde and allopurinol possess anti-oxidative and anti-inflammatory activity to relieve heart injury in metabolic syndrome. But the mechanisms of fructose-induced cardiac injury and cardioprotective effects of cinnamaldehyde and allopurinol are not completely understood. In this study, fructose-fed rats displayed metabolic syndrome with elevated serum ox-LDL, cardiac oxidative stress, inflammation and fibrosis. Scavenger receptor CD36, Toll-like receptor 4 (TLR4), TLR6, IL-1R-associated kinase 4/1 (IRAK4/1), nucleotide-binding domain (NOD)-like receptor protein 3 (NLRP3) inflammasome, interleukin-1β, transforming growth factor-β (TGF-β), drosophila mothers against DPP homolog (Smad) 2/3 phosphorylation and Smad4 were increased in animal and H9c2 cell models. These pathological processes were further evaluated in ox-LDL or fructose-exposed H9c2 cells pretreated with ROS scavenger and CD36 specific inhibitor, or IRAK1/4 inhibitor and transfected with CD36, NLRP3, or IRAK4/1 siRNA, demonstrating that NLPR3 inflammasome activation through CD36-mediated TLR4/6-IRAK4/1 signaling may promote cardiac inflammation and fibrosis. Cinnamaldehyde and allopurinol reduced cardiac oxidative stress to suppress NLPR3 inflammasome activation and TGF-β/Smads signaling by inhibiting CD36-mediated TLR4/6-IRAK4/1 signaling under fructose induction. These results suggest that the blockage of CD36-mediated TLR4/6-IRAK4/1 signaling to suppress NLRP3 inflammasome activation by cinnamaldehyde and allopurinol may protect against fructose-induced cardiac inflammation and fibrosis.