Multilingual and Indian-Language NLP
Translation, transliteration and processing for Hindi and other Indian and world languages.
Intermediate
This is an overview — pick a sub-topic below.
Sub-topics (5)
Indic NLP
Process Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Punjabi, Urdu and Sanskrit text.
Intermediate♥ 0🔖 0💬 0
Machine Translation and Language Identification
Translate text and detect which language it is.
Intermediate♥ 0🔖 0💬 0
Transliteration and Unicode Normalization
Convert between scripts (Devanagari ↔ Latin) and normalise Unicode text.
Intermediate♥ 0🔖 0💬 0
Arabic, Chinese, Japanese, Korean and Thai NLP
Languages without spaces or with complex morphology need special tokenizers.
Advanced♥ 0🔖 0💬 0
Low-Resource Languages and Multilingual Embeddings
Techniques for languages with little data: cross-lingual transfer and multilingual models.
Advanced♥ 0🔖 0💬 0
Spotted a mistake or want to add detail? Suggest an improvement — Content Contributors' edits are reviewed by editors before they go live.
Discussion (0)
Sign in or join free to ask questions and discuss this topic.