Pre-trained Word Embedding based Parallel Text Augmentation Technique for Low-Resource NMT in Favor of Morphologically Rich Languages.
Tulu Tilahun HailuJunqing YuTessfu Geteye FantayePublished in: CSAE (2019)
Keyphrases
- pre trained
- english text
- word forms
- language specific
- syntactic categories
- multiword
- text summarization
- character n grams
- language independent
- machine translation system
- indian languages
- n gram
- word pairs
- training examples
- control signals
- training data
- neural network
- text mining
- target language
- small number
- learning algorithm
- cross lingual
- machine translation
- document images