Summary of Clustertabnet: Supervised Clustering Method For Table Detection and Table Structure Recognition, by Marek Polewczyk and Marco Spinaci
ClusterTabNet: Supervised clustering method for table detection and table structure recognition
by Marek Polewczyk, Marco Spinaci
First submitted to arxiv on: 12 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
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 a novel deep-learning-based approach to clustering words in documents, which is applied to detect and recognize tables given OCR output. The method interprets table structure as a graph of relations between word pairs and uses a transformer encoder model to predict the adjacency matrix. On three benchmark datasets (PubTables-1M, PubTabNet, and FinTabNet), the proposed method outperforms current state-of-the-art detection methods like DETR and Faster R-CNN in terms of accuracy while requiring smaller models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps computers better understand documents by organizing words into groups. It uses a new way to recognize tables within these groups based on how words relate to each other. The method is tested on large datasets and performs as well or even better than existing methods, but with less complex models. This could be useful in many areas, such as document analysis and data extraction. |
Keywords
* Artificial intelligence * Clustering * Cnn * Deep learning * Encoder * Transformer
