LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding.
Yi TuYa GuoHuan ChenJinyang TangPublished in: CoRR (2023)
Keyphrases
- multi modal
- document understanding
- automatic text summarization
- automatic summarization
- video search
- designing effective
- multi document summarization
- document clustering
- text mining
- text retrieval
- multiple modalities
- text documents
- cross modal
- lexical chains
- text summarization
- high dimensional
- multi modality
- keywords
- image annotation
- document summarization
- information retrieval
- language independent
- document retrieval
- image classification
- language model