High Frequent In-domain Words Segmentation and Forward Translation for the WMT21 Biomedical Task.
Bardia RafieianMarta Ruiz Costa-jussàPublished in: WMT@EMNLP (2021)
Keyphrases
- word segmentation
- cursive script
- segmentation algorithm
- image segmentation
- biomedical image analysis
- domain specific
- level set
- numeral strings
- segmentation method
- shape prior
- machine translation
- medical images
- english words
- biomedical images
- multiscale
- frequency counts
- object segmentation
- word sense disambiguation
- region growing
- text documents
- n gram
- text mining
- information extraction
- related words
- parallel corpus
- out of vocabulary
- mathematical methods
- keywords
- genia corpus