ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
ERNIE-Layout enhances document pre-training with layout knowledge for improved visually-rich document understanding.
Published 202265 citationsCode ★ 106Paper ↗
72%
OverallHighly rated
?
OverallHighly ratedVote to see the scoreThe exact score shows once you've voted, so every vote is your own call. The first half of each home page shelf shows its scores.
Readers
–
Only vote on papers you've read. Sign in with GitHub to vote.
AI panel8/21reviewers recommend it
lenient 4/5
medium 4/11
strict 0/5
AI panel?Vote to see what the 20 AI reviewers said
ERNIE-Layout offers a lecture-grade framework binding geometry to semantics, though its heavy pretraining and masked-coordinate design lack independent uptake proof and parameter-efficient benchmarks.
Abstract
Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang. Findings of the Association for Computational Linguistics: EMNLP 2022. 2022.