Research on the Construction of Resource Database of the Yi Dialects for Information Processing in China

Abstract

At present, the research on the basic language project of the Yi language is still in the primary stage, so it is not easy to describe and show the real features of the Yi dialects. How to establish a corpus of Yi dialects with the help of computer information, corpus, artificial intelligence, and other modern information processing technologies, indeed record the appearance and situation of Yi dialects, and protect Yi language cultural heritage with social and historical value has become a critical problem to be solved in Yi language and related research fields. This paper takes the six major Yi dialects as the main line of research, combined with the characteristics and application scope and population size of different Yi dialects, to determine the language survey analysis and data collection points of each dialect, subdialect, and local language point. On this basis, carry out the research and construction of the Yi dialects resource database from multiple levels and dimensions such as words, sentences, dialogues, and texts, and create a high-quality information sharing platform of Yi dialects corpus. Moreover, combined with the author's practical experience in the research and development of Yi language information processing technology, this paper analyzes and considers some related problems in the construction and application of Yi dialects corpus.