This paper gives the overview of the language resources developed for a less-resourced western Indo-Aryan language of India - Braj Bhasha. There is no language resource available for Braj Bhasha. The paper gives the detail of first-ever language resources developed for Braj Bhasha which are text corpus, BIS based POS tagset and annotation, Universal Dependency (UD) based morphological and dependency annotation. UD is a framework for cross-linguistically consistent grammatical annotation and an open community effort with contributors working on over 60 languages. The methodology used to develop corpus, tagset, and annotation can help in creating resources for other less-resourced languages. These resources would provide the opportunity for Braj Bhasha to develop NLP applications and to do research on various areas of linguistics - cognitive linguistics, comparative linguistics, typological and theoretical linguistics.
@InProceedings{JAIN18.24, author = {Mayank Jain ,Yogesh Dawer ,Nandini Chauhan and Anjali Gupta}, title = {Developing Resources for a Less Resourced Language: Braj Bhasha}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {may}, date = {7-12}, location = {Miyazaki, Japan}, editor = {Girish Nath Jha and Kalika Bali and Sobha L and Atul
Kr. Ojha}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {979-10-95546-09-2}, language = {english} }
Summary of the paper