3 code implementations • 8 Jun 2021 • Antonio Jimeno Yepes, Xu Zhong, Douglas Burdick
Scientific literature contain important information related to cutting-edge innovations in diverse domains.
no code implementations • NAACL 2021 • Ying Xu, Xu Zhong, Antonio Jimeno Yepes, Jey Han Lau
We introduce a grey-box adversarial attack and defence framework for sentiment classification.
no code implementations • 1 May 2020 • Xinyi Zheng, Doug Burdick, Lucian Popa, Xu Zhong, Nancy Xin Ru Wang
With GTE-Table, we invent a new penalty based on the natural cell containment constraint of tables to train our table network aided by cell location predictions.
no code implementations • 22 Jan 2020 • Ying Xu, Xu Zhong, Antonio Jose Jimeno Yepes, Jey Han Lau
An adversarial example is an input transformed by small perturbations that machine learning models consistently misclassify.
6 code implementations • ECCV 2020 • Xu Zhong, Elaheh ShafieiBavani, Antonio Jimeno Yepes
In addition, we propose a new Tree-Edit-Distance-based Similarity (TEDS) metric for table recognition, which more appropriately captures multi-hop cell misalignment and OCR errors than the pre-established metric.
Ranked #10 on Table Recognition on PubTabNet
Information Retrieval Optical Character Recognition (OCR) +2
no code implementations • WS 2020 • Elaheh ShafieiBavani, Antonio Jimeno Yepes, Xu Zhong, David Martinez Iraola
Due to the exponential growth of biomedical literature, event and relation extraction are important tasks in biomedical text mining.
6 code implementations • 16 Aug 2019 • Xu Zhong, Jianbin Tang, Antonio Jimeno Yepes
Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images.
Ranked #11 on Document Layout Analysis on PubLayNet val