Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages
This work addresses a domain-specific need for language identification in Indian languages, particularly for romanized text, which has limited prior work, but it is incremental in extending existing methods to new data and scripts.
The authors tackled the problem of language identification for 22 Indic languages in both native-script and romanized text by creating public datasets and models, achieving competitive or better performance for native-script and being the first to address romanized text with effective solutions for data scarcity and low performance on similar languages.
We create publicly available language identification (LID) datasets and models in all 22 Indian languages listed in the Indian constitution in both native-script and romanized text. First, we create Bhasha-Abhijnaanam, a language identification test set for native-script as well as romanized text which spans all 22 Indic languages. We also train IndicLID, a language identifier for all the above-mentioned languages in both native and romanized script. For native-script text, it has better language coverage than existing LIDs and is competitive or better than other LIDs. IndicLID is the first LID for romanized text in Indian languages. Two major challenges for romanized text LID are the lack of training data and low-LID performance when languages are similar. We provide simple and effective solutions to these problems. In general, there has been limited work on romanized text in any language, and our findings are relevant to other languages that need romanized language identification. Our models are publicly available at https://ai4bharat.iitm.ac.in/indiclid under open-source licenses. Our training and test sets are also publicly available at https://ai4bharat.iitm.ac.in/bhasha-abhijnaanam under open-source licenses.