Visually Guided Generative Text-Layout Pre-training for Document Intelligence.
Zhiming MaoHaoli BaiLu HouJiansheng WeiXin JiangQun LiuKam-Fai WongPublished in: CoRR (2024)
Keyphrases
- visually guided
- cf loadingtexthtml
- text documents
- information retrieval
- digital documents
- web documents
- textual content
- text classifiers
- keywords
- document analysis
- text content
- document content
- page layout
- document processing
- text collections
- document images
- document structure
- training corpus
- document image retrieval
- text mining
- document layout
- text retrieval
- text classification
- generative model
- text corpus
- text fragments
- text summarization
- information retrieval systems
- scientific papers
- multimedia documents
- document retrieval
- document corpus
- semantic information
- latent semantic analysis
- document level
- discriminative training
- electronic documents
- printed documents
- automatic text summarization
- web pages
- relevant documents
- scientific documents
- tf idf
- document set