Software Resources and Data sets

The following resources are available. Please contact us if you like to try these out:

Tools:

• Si-Ta - Machine translation system for Sinhala and Tamil
• Thamizhi-POS
• ThamizhiMorph
• ThamizhiUDp
• SinMorphy Sinhala Morphological Analyzer

Data/Trained models:

• Sinhala POS-tagged data (~250,000 tokens)
• Sinhala-Tamil Aligned - Parallel Corpus (~1100 pairs)
• Sinhala and Tamil FastText Models
• Named Entity annotated corpus
• English-Tamil Corpus
• Sinhala Stopword list