LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages

Milind Agarwal, Md Mahfuz Ibn Alam, Antonios Anastasopoulos


Abstract
Knowing the language of an input text/audio is a necessary first step for using almost every NLP tool such as taggers, parsers, or translation systems. Language identification is a well-studied problem, sometimes even considered solved; in reality, due to lack of data and computational challenges, current systems cannot accurately identify most of the world’s 7000 languages. To tackle this bottleneck, we first compile a corpus, MCS-350, of 50K multilingual and parallel children’s stories in 350+ languages. MCS-350 can serve as a benchmark for language identification of short texts and for 1400+ new translation directions in low-resource Indian and African languages. Second, we propose a novel misprediction-resolution hierarchical model, LIMIT, for language identification that reduces error by 55% (from 0.71 to 0.32) on our compiled children’s stories dataset and by 40% (from 0.23 to 0.14) on the FLORES-200 benchmark. Our method can expand language identification coverage into low-resource languages by relying solely on systemic misprediction patterns, bypassing the need to retrain large models from scratch.
Anthology ID:
2023.emnlp-main.895
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14496–14519
Language:
URL:
https://aclanthology.org/2023.emnlp-main.895
DOI:
10.18653/v1/2023.emnlp-main.895
Bibkey:
Cite (ACL):
Milind Agarwal, Md Mahfuz Ibn Alam, and Antonios Anastasopoulos. 2023. LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14496–14519, Singapore. Association for Computational Linguistics.
Cite (Informal):
LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages (Agarwal et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.895.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.895.mp4