NLP for Low Resource Languages of South Asia

South Asia is rich in languages. For example, even Nepal with a relatively moderate population size has more than 100 spoken languages (not just dialects!). However, even the most widely spoken language in Nepal, Nepali, has limited data and resources. Thus, one cannot easily leverage recent advancements in Natural Language Processing (NLP) and AI such as large transformer models that need a large amount of data and computing resources. We explore more efficient methods useful for various steps of NLP including language models. Developing AI models that can better understand these languages will make AI more inclusive as one can develop tools and applications such as chatbots and voice bots for the non-English speaking population. This will also increase the access to digital technology that is rapidly being transformed with AI.