MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding.
Junlong LiYiheng XuLei CuiFuru WeiPublished in: CoRR (2021)
Keyphrases
- markup language
- document understanding
- automatic text summarization
- automatic summarization
- designing effective
- multi document summarization
- text summarization
- text mining
- document clustering
- information retrieval
- text documents
- high level
- lexical chains
- database
- machine learning
- document summarization
- xml schema
- language independent
- text retrieval
- keywords
- web pages
- databases