Spelling Normalization of Historical Documents by Using a Machine Translation Approach.
Miguel DomingoFrancisco CasacubertaPublished in: EAMT (2018)
Keyphrases
- machine translation
- historical documents
- handwriting recognition
- document images
- language independent
- word recognition
- natural language processing
- cross lingual
- information extraction
- statistical machine translation
- cross language information retrieval
- target language
- chinese english
- word sense disambiguation
- natural language
- co occurrence
- word level
- handwritten documents
- language resources
- machine learning
- query translation
- pattern recognition
- word segmentation
- metadata
- vision system
- machine translation system
- document image analysis
- information retrieval