Summary of Graph Contrastive Learning Via Cluster-refined Negative Sampling For Semi-supervised Text Classification, by Wei Ai et al.
Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classification
by Wei Ai, Jianbin Li, Ze Wang, Jiayi Du, Tao Meng, Yuntao Shou, Keqin Li
First submitted to arxiv on: 18 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes an innovative approach to semi-supervised text classification called ClusterText. It combines pre-trained BERT models with graph neural networks to learn text representations, then refines these representations by clustering them into pseudo labels. The authors introduce a novel negative sampling strategy that draws samples from different clusters, reducing the impact of over-clustering. Additionally, they propose a self-correction mechanism to mitigate errors caused by clustering inconsistency. Experimental results show ClusterText’s effectiveness in text classification tasks, demonstrating its ability to extract important information from large datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper talks about how to make computers better at understanding written language. It uses two techniques: one that learns patterns from lots of text data, and another that groups similar texts together. The authors want to help computers avoid grouping too many similar texts together, which can be a problem. They propose a new way of doing this, called ClusterText, which seems to work well in tests. This is important because it could help computers understand written language more accurately and quickly. |
Keywords
» Artificial intelligence » Bert » Clustering » Semi supervised » Text classification
