Summary of Autore: Document-level Relation Extraction with Large Language Models, by Lilong Xue and Dan Zhang and Yuxiao Dong and Jie Tang
AutoRE: Document-Level Relation Extraction with Large Language Models
by Lilong Xue, Dan Zhang, Yuxiao Dong, Jie Tang
First submitted to arxiv on: 21 Mar 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 This paper introduces AutoRE, an end-to-end model for Document-Level Relation Extraction (DocRE) tasks. Unlike existing methods that rely on predefined relation options, AutoRE adopts a novel paradigm called RHF (Relation-Head-Facts) and does not assume known relation choices. The authors develop an easily extensible RE framework using the Parameters Efficient Fine Tuning (PEFT) algorithm (QLoRA). They demonstrate their approach’s effectiveness on the RE-DocRED dataset, achieving state-of-the-art results that outperform TAG by 10.03% and 9.03% respectively on the dev and test sets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AutoRE is a new way to find relationships between things in documents. Instead of guessing what kind of relationship might be there, AutoRE looks at all the words in the document to figure it out. This makes it better than other methods that rely on knowing what kinds of relationships are possible beforehand. The authors also created a special way to make their model work well with different types of data and tasks. |
Keywords
* Artificial intelligence * Fine tuning
