Linguistically enhanced word segmentation for better neural machine translation of low resource agglutinative languages.
Santwana ChimalamarriDinkar SitaramPublished in: Int. J. Speech Technol. (2021)
Keyphrases
- word segmentation
- machine translation
- language independent
- cross lingual
- target language
- word level
- word recognition
- pos tagging
- handwriting recognition
- n gram
- information extraction
- language specific
- natural language
- natural language processing
- cross language
- statistical machine translation
- cross language information retrieval
- parallel corpora
- machine translation system
- out of vocabulary
- text classification
- multilingual documents
- language resources
- word sense disambiguation
- source language
- translation model
- language modeling
- active learning