Summary of Vrdsynth: Synthesizing Programs For Multilingual Visually Rich Document Information Extraction, by Thanh-dat Nguyen et al.
VRDSynth: Synthesizing Programs for Multilingual Visually Rich Document Information Extraction
by Thanh-Dat Nguyen, Tung Do-Viet, Hung Nguyen-Duy, Tuan-Hai Luu, Hung Le, Bach Le, Patanamon, Thongtanunam
First submitted to arxiv on: 9 Jul 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 paper introduces VRDSynth, a program synthesis method for extracting entity relations from visually rich documents (VRDs) without pre-training data. The approach uses a domain-specific language (DSL) to capture spatial and textual relations in the VRDs, enabling the automatic extraction of entities without extensive training. The algorithm utilizes frequent spatial relations, search space pruning, and a combination of positive, negative, and exclusive programs to improve coverage. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Businesses need to query visually rich documents like receipts and medical records to make decisions. Existing methods struggle with new layouts or require lots of pre-training data. This paper introduces VRDSynth, a program that can extract entity relations from these documents without needing training. It uses special language rules to understand the document’s layout and content. |
Keywords
» Artificial intelligence » Pruning
