no code implementations • 16 May 2023 • Shuwei Feng, Tianyang Zhan, Zhanming Jie, Trung Quoc Luong, Xiaoran Jin
This paper presents GenDoc, a general sequence-to-sequence document understanding model pre-trained with unified masking across three modalities: text, image, and layout.
document understanding Optical Character Recognition (OCR) +1
1 code implementation • 27 Feb 2022 • Zhuang Li, Lizhen Qu, Qiongkai Xu, Tongtong Wu, Tianyang Zhan, Gholamreza Haffari
In this paper, we propose a variational autoencoder with disentanglement priors, VAE-DPRIOR, for task-specific natural language generation with none or a handful of task-specific labeled examples.
1 code implementation • 7 Jan 2021 • Hongjing Zhang, Tianyang Zhan, Sugato Basu, Ian Davidson
A fundamental strength of deep learning is its flexibility, and here we explore a deep learning framework for constrained clustering and in particular explore how it can extend the field of constrained clustering.