TableBank: A Benchmark Dataset for Table Detection and Recognition
This provides a large-scale benchmark dataset to improve deep learning approaches for table detection and recognition, addressing a domain-specific need in document analysis.
The authors tackled the problem of limited generalization in image-based table detection and recognition by creating TableBank, a dataset of 417K labeled tables built with weak supervision from online documents, and established strong baselines using state-of-the-art deep neural network models.
We present TableBank, a new image-based table detection and recognition dataset built with novel weak supervision from Word and Latex documents on the internet. Existing research for image-based table detection and recognition usually fine-tunes pre-trained models on out-of-domain data with a few thousand human-labeled examples, which is difficult to generalize on real-world applications. With TableBank that contains 417K high quality labeled tables, we build several strong baselines using state-of-the-art models with deep neural networks. We make TableBank publicly available and hope it will empower more deep learning approaches in the table detection and recognition task. The dataset and models are available at \url{https://github.com/doc-analysis/TableBank}.