The workshop aims to provide a space for reflecting on the steps needed to adapt and evolve current state-of-the-art methods & software tools available for document analysis for Indian regional languages. The main goal of the workshop is to accelerate the research and development of document analysis tools so that the performance of such tools is at par with other Latin-based languages, which we are currently lagging. We have discussed SOTA work in the broad spectrum of document analysis and its import to Indian languages.

We have discussed available datasets or corpora for major Indian languages, Deep Neural-Network based Computer Vision and Language Models that can be used for various downstream tasks of document analysis; They form the foundational basis for performing Document Analysis for the regional languages.

The driving idea behind the workshop comes from the fact that there is a large scope for improvement in adapting and creating new techniques and methods in the many fields of document analysis from the context of Indian regional languages. With its unique structure and clear diversity from Latin-based languages, there is a need to focus on clearly understanding the space and filling that gap that exists.