Our Portfolio
Showcasing our ongoing projects in NLP resource creation, linguistic analysis, and technology development for low-resource languages.
🗣️
Corpus Creation
Bhojpuri Speech Corpora
Bootstrapped extensive NLP resources and speech corpora for the Bhojpuri language to support the Govt. of India funded Sampark Machine Translation System.
View Project
🤖
Machine Translation
Maithili & Magahi MT
Conducted typological analysis and POS labelling to generate critical language data experiments for low-resource Indian languages.
View Project
📝
Linguistic Tools
Advanced POS Tagger
Text chunking, data generation, and morpho-syntactic feature annotation designed specifically for scheduled and low-resource Indian languages.
View Project