Biqing Zeng

Combining Syntactic Information Enhancement and Graph Convolutional Network for Aspect-level Sentiment Analysis

2023

In this paper, we suggest a way to address this issue by combining the Syntactic Attention Network with syntactic information augmentation. Syntactic Information Enhancement - Graph Convolutional Network (SIE-GCN) aspect-level sentiment analysis model. This model …

Multi-Encoder with Entity-Aware Embedding Framework for Distantly Supervised Relation Extraction

2023

Distantly supervised relation extraction (DSRE) inherently faces challenges arising from labeling noise due to the distant supervision assumption. Most existing studies employ Piece-wise CNN (PCNN) to extract semantic features from sentences, often neglecting to comprehensively …

Enhancing Few-Shot Classification without Forgetting Through Multi-level Contrastive Constraints

2024

Most recent few-shot learning approaches are based on meta-learning with episodic training. However, prior studies encounter two crucial problems: (1) the presence of inductive bias, and (2) the occurrence of catastrophic forgetting. In this paper, …