Cornell University
X
A new study presents BhashaSetu, featuring the innovative GETR (Graph-Enhanced Token Representation) method for cross-lingual knowledge transfer to extremely low-resource languages with just hundreds of labeled examples.
The research focuses on improving performance for both sentence-level and word-level NLP tasks in Indian languages. The GETR approach leverages graph neural networks to transfer linguistic knowledge from high-resource languages, outperforming existing multilingual methods.
Results show significant improvements: 13 percentage points for POS tagging in truly low-resource languages like Mizo and Khasi, and impressive gains of 20 and 27 percentage points in macro-F1 scores for sentiment classification and named entity recognition in simulated low-resource languages (Marathi, Bangla, Malayalam).
The study also analyzes the specific mechanisms that make cross-lingual knowledge transfer successful in this context, providing insights for future work on computational linguistics for under-represented languages.
NALCO Wins Award for Hindi Implementation in Official Work
Punjab Board Introduces Bilingual Urdu-English DIT Exams
Canara Bank Hosts All India Hindi Seminar in Delhi
Visakhapatnam Railway Office Tops Hindi Implementation
Uttarakhand to Establish Sanskrit Commission
Maharashtra CM's Office Calls for Marathi Language Action Plan