Papers by Shuigeng Zhou

4 papers
Weakly-supervised Text Classification Based on Keyword Graph (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for text classification ignore keyword correlation, thus ignoring it . existing methods treat keywords independently, thus not exploiting correlation between them .
Approach: They propose a framework to explore keyword-keyword correlation on keyword graph by GNN . they use a self-supervised task to pretrain annotators and fine-tune them .
Outcome: The proposed method outperforms existing methods on long- and short-text datasets.
EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods for data augmentation do not fully exploit the potential of DA in NLP.
Approach: They propose an easy and plug-in framework for data augmentation to support effective text classification.
Outcome: The proposed framework outperforms existing methods in most cases, but not using agent networks or pre-trained generation networks.
VENUS: A VLLM-driven Video Content Discovery System for Real Application Scenarios (2025.emnlp-industry)

Copied to clipboard

Challenge: Video Content Discovery (VCD) is to identify specific videos defined by a pre-specified text policy.
Approach: They propose a Vision-Language Large Model-driven video content discovery system called VENUS to solve these problems.
Outcome: The proposed system generates high-quality, VCD-specific data for model training and extends it to support it better.
Multi-matrix Factorization Attention (2025.findings-acl)

Copied to clipboard

Challenge: Existing variants for Multi-Head Attention (MHA) fail to maintain strong performance under stringent Key-Value cache (KV cache) constraints.
Approach: They propose to use multi-matrix factorization attention and MFA-Key-reuse attention architectures to increase model capacity under tight KV cache constraints.
Outcome: The proposed architecture outperforms existing methods while reducing KV cache usage by 56% and 93.7% in large-scale experiments.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations