Summary of Vaediff-docre: End-to-end Data Augmentation Framework For Document-level Relation Extraction, by Khai Phan Tran et al.
VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction
by Khai Phan Tran, Wen Hua, Xue Li
First submitted to arxiv on: 18 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 In this paper, researchers develop a novel approach to improve Document-level Relation Extraction (DocRE) models by enhancing data from the embedding space. The proposed method uses Variational Autoencoders (VAEs) and Diffusion Models to capture relation-wise distributions formed by entity pair representations and augment data for underrepresented relations. The authors also introduce a hierarchical training framework that integrates this augmentation module into DocRE systems. Experimental results show that their approach outperforms state-of-the-art models on two benchmark datasets, effectively addressing the long-tail distribution problem in DocRE. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a way to make computers better at understanding relationships between things mentioned in documents. Right now, most computer programs have trouble with this because they’re not good at dealing with situations where some relationships are much more common than others. The researchers came up with a new approach that uses special kinds of artificial intelligence models to help computers learn about these less common relationships too. They tested their idea and found that it works better than what’s currently available. |
Keywords
» Artificial intelligence » Embedding space
