LayoutLM: Pre-training of Text and Layout for Document Image Understanding.
Yiheng XuMinghao LiLei CuiShaohan HuangFuru WeiMing ZhouPublished in: KDD (2020)
Keyphrases
- document image understanding
- document images
- page layout
- training set
- information retrieval
- document layout
- document analysis
- supervised learning
- training examples
- text retrieval
- test set
- training algorithm
- data mining
- free text
- text mining
- data sets
- web documents
- text categorization
- training samples
- textual information
- automatically extracted
- text content
- learning algorithm
- neural network