AI4Bharat - MultiIndic Model for Sentence-level Question Generation
MultiIndicQuestionGenerationSS is a multilingual, sequence-to-sequence pre-trained model fine-tuned on the IndicQuestionGeneration dataset for question generation across 11 Indian languages.
About Model
MultiIndicQuestionGenerationSS is a sequence-to-sequence pre-trained model based on IndicBARTSS, fine-tuned on the IndicQuestionGeneration dataset, supporting 11 Indian languages: Hindi, Marathi, Punjabi, Tamil, Telugu, Bengali, Gujarati etc. Smaller than mBART and mT5, it is computationally efficient for fine-tuning and decoding. Trained on a large corpus of 770K examples, each language is represented in its own script, removing the need for Devanagari script mapping, making it ideal for question generation tasks in multiple Indian languages.
AI4Bharat - MultiIndic Model for Sentence-level Question Generation
Metadata
MIT
Aman Kumar, Himani Shrotriya, Prachi Sahu, Raj Dabre, Ratish Puduppully, Anoop Kunchukuttan, Amogh Mishra, Mitesh M. Khapra, Pratyush Kumar
Text Generation
N.A.
Open
Sector Agnostic
21/02/25 13:20:52
0
Activity Overview
0
2 
166 
0
Tags
- Multilingual
- AI4Bharat
- NLP
- Deep Learning
- Question Generation
- Text Generation
License Control
MIT
Related Datasets
More Models from AI4Bharat
- 1
- 16
- 0
209
- 3
- 204
- 0
- 2,562
- 0
- 2
- 0
- 166
- 0
- 0
- 0
- 98
- 0
- 0
- 0
- 48
- 1
- 6
- 0
- 67
- 0
- 1
- 0
- 57
- 1
- 1
- 0
- 49
- 0
- 0
- 0
- 292
- 0
- 6
- 0
- 149
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.