Papers by Milind Agarwal
LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages (2023.emnlp-main)
Copied to clipboard
| Challenge: | Currently, existing systems cannot accurately identify most of the world's 7000 languages due to lack of data and computational challenges. |
| Approach: | They propose a misprediction-resolution hierarchical model, LIMIT, that reduces error by 55% on a children's stories dataset and by 40% on 'fLORES-200' benchmark. |
| Outcome: | The proposed model reduces error by 55% on the MCS-350 and 40% on the FLORES-200 benchmarks. |
Script-Agnosticism and its Impact on Language Identification for Dravidian Languages (2025.naacl-long)
Copied to clipboard
| Challenge: | a recent study shows that modern systems are script-dependent in language identification (langID) many languages are written in multiple writing systems, and script diversity is common in low-resource languages. |
| Approach: | They propose to learn script-agnostic representations using different strategies . they use word-level script randomization and script exposure to a language written in multiple scripts . |
| Outcome: | The proposed methods exploit script randomization and exposure to a language written in multiple scripts to improve language identification while maintaining competitive performance on naturally occurring text. |