@inproceedings{f0cb390c086347628d441921891f04a0,
title = "TableBank: Table benchmark for image-based table detection and recognition",
abstract = "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 can be downloaded from https://github.com/doc-analysis/TableBank.",
keywords = "Image-based deep learning network, Table detection and recognition, TableBank, Weak supervision",
author = "Minghao Li and Lei Cui and Shaohan Huang and Furu Wei and Ming Zhou and Zhoujun Li",
note = "Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC; 12th International Conference on Language Resources and Evaluation, LREC 2020 ; Conference date: 11-05-2020 Through 16-05-2020",
year = "2020",
language = "英语",
series = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "1918--1925",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis",
booktitle = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
}