The first comprehensive survey is presented of natural language processing (NLP) research in Konkani, a low-resource regional Indian language with a small population of native speakers. The combined challenges of complex linguistic phenomena, paucity of documented resources and the presence of neighboring dominant languages are elaborated. The possibilities of crowdsourcing as a means for creating linguistic resources are explored.

中文翻译：

---

Konkani NLP资源调查

首次全面调查是在Konkani（自然资源处理（NLP）研究）中进行的，这是一种资源匮乏的印度当地语言，母语为母语的人口很少。详细阐述了复杂的语言现象，文献资源匮乏以及相邻主要语言的存在所带来的综合挑战。探索了将众包作为创建语言资源的手段的可能性。