Summary of The Solution For the Pst-kdd-2024 Oag-challenge, by Shupeng Zhong et al.
The Solution for The PST-KDD-2024 OAG-Challenge
by Shupeng Zhong, Xinger Li, Shushan Jin, Yang Yang
First submitted to arxiv on: 2 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 The proposed approach is a second-place solution in the KDD-2024 OAG-Challenge paper source tracing track that leverages BERT and GCN to achieve complementary performance. The BERT-based method focuses on processing paper fragments, reducing redundant interference, and refining information received by the model. In contrast, the GCN-based method maps paper-related information to a high-dimensional semantic space, integrating contextual relationships through edge building. By combining these approaches, the solution achieves a remarkable score of 0.47691 in the competition. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper presents an innovative approach to tracing the source of papers. It combines two powerful methods, BERT and GCN, to analyze paper fragments, abstracts, and titles. The goal is to identify relationships between these elements and make accurate judgments. The method first refines information from paper fragments using BERT and then maps this information to a high-dimensional space for contextual analysis with GCN. By combining these approaches, the researchers achieved impressive results in the KDD-2024 OAG-Challenge. |
Keywords
» Artificial intelligence » Bert » Gcn
