Unsupervised Separation of Native and Loanwords for Malayalam and Telugu.
Sridhama PrakhyaDeepak PPublished in: CoRR (2020)
Keyphrases
- indian languages
- document images
- language identification
- character recognition
- cross lingual
- semi supervised
- data driven
- unsupervised learning
- supervised learning
- word segmentation
- neural network
- machine learning
- word level
- unsupervised manner
- document analysis
- text data
- data sets
- text mining
- high dimensional
- training data