Language and NLP Section 053
Multilingual and Indic NLP
Making NLP work in Hindi, Marathi, Tamil and Hinglish — not only in English.
12 of 12 lessons published Three reading levels on every lesson
Lessons in order
Work top to bottom. Each lesson assumes the one above it.
- How neural machine translation works
- Running translation models yourself
- Translating a low-resource language
- XLM-RoBERTa and multilingual encoders
- Train in English, run in Hindi
- Multilingual sentence embeddings
- Question in Hindi, documents in English
- Hinglish and code-mixed text
- Transliteration between scripts
- Normalising Indic scripts
- The AI4Bharat and IndicNLP stack
- Why Hindi costs three times more tokens than English