TransIns: Document Translation with Markup Reinsertion.
Jörg SteffenJosef van GenabithPublished in: EMNLP (Demos) (2021)
Keyphrases
- document structure
- document images
- information retrieval
- document collections
- information retrieval systems
- document classification
- machine translation
- retrieval systems
- text documents
- neural network
- source language
- content and structure
- multimedia documents
- document representation
- document retrieval
- relevant documents
- keywords
- database
- document clustering
- user queries
- cross language information retrieval
- markup language
- semantic information
- document analysis
- statistical machine translation
- web documents
- word level