Papers by Chang-Bo Liu

1 papers
STSPL-SSC: Semi-Supervised Few-Shot Short Text Clustering with Semantic text similarity Optimized Pseudo-Labels (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for obtaining task-specific labels require prior knowledge of clustering categories and uncontrollable clustering centers.
Approach: They propose a framework for supervised clustering using a discrete process and a robust Contrastive Learning module.
Outcome: The proposed framework outperforms state-of-the-art models on a real-world dataset with just one label per class . the proposed framework is based on k-means clustering and a robust Contrastive Learning module .

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