Papers by Guodong Zheng

2 papers
More than Text: Multi-modal Chinese Word Segmentation (2021.acl-short)

Copied to clipboard

Challenge: Currently, word segmentation is performed in many languages without word delimiters.
Approach: They propose to combine the multi-modality to perform Chinese word segmentation . they propose a time-dependent multi-module interactive model to integrate multi-modality information .
Outcome: The proposed model integrates multi-modal information for word sequence labeling with Chinese language as target . the proposed model performs well on three training sets on Chinese and other languages without word delimiters.
Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)

Copied to clipboard

Challenge: Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations.
Approach: They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference.
Outcome: The proposed method significantly mitigates object hallucinations across various model architectures.

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