no code implementations • COLING (TextGraphs) 2020 • Chuwei Luo, Yongpan Wang, Qi Zheng, Liangchen Li, Feiyu Gao, Shiyu Zhang
By incorporating geometry information from visual documents into our model, richer 2D context information is generated to improve document representations.
3 code implementations • 8 Apr 2024 • Chuwei Luo, Yufan Shen, Zhaoqing Zhu, Qi Zheng, Zhi Yu, Cong Yao
The core of LayoutLLM is a layout instruction tuning strategy, which is specially designed to enhance the comprehension and utilization of document layouts.
1 code implementation • ICCV 2023 • Cheng Da, Chuwei Luo, Qi Zheng, Cong Yao
Document pre-trained models and grid-based models have proven to be very effective on various tasks in Document AI.
Ranked #1 on Document Layout Analysis on PubLayNet val
1 code implementation • CVPR 2023 • Chuwei Luo, Changxu Cheng, Qi Zheng, Cong Yao
Additionally, novel relation heads, which are pre-trained by the geometric pre-training tasks and fine-tuned for RE, are elaborately designed to enrich and enhance the feature representation.
Ranked #1 on Key Information Extraction on CORD
no code implementations • 27 Jun 2022 • Chuwei Luo, Guozhi Tang, Qi Zheng, Cong Yao, Lianwen Jin, Chenliang Li, Yang Xue, Luo Si
Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks.
no code implementations • 28 Nov 2016 • Ziqiang Cao, Chuwei Luo, Wenjie Li, Sujian Li
In this paper, we develop a novel Seq2Seq model to fuse a copying decoder and a restricted generative decoder.