In machine translation, the training of the model requires bilingual data: original text data and target language data. The translation of literary Chinese is very special, as it’ s not a language used in daily life. Only when data volume is large enough and its quality high enough can you train a more accurate model. The most critical element of AI model training is data. With the help of machine translation, tourists can now understand ancient Chinese texts and poems written on historic buildings and monuments, students now have an extra tool to help them learn Chinese, and researchers who are engaged in collating and translating ancient texts can be more productive.ĭongdong Zhang, a principal researcher at Microsoft Research Asia, said, “From a technical perspective, literary Chinese can be regarded as a separate language. Once translation between literary Chinese and modern Chinese is realized, the translation between literary Chinese and other languages such as English, French, and German becomes a matter of course.”īiggest difficulty of literary Chinese translation AI model: Little training data The thoughts and wisdom accumulated and contained in them are worthy of continuous exploration and thinking. Voluminous books and texts from the ancient times have recorded China ’ s rich and profound culture over the past five thousand years. Literary Chinese is an important carrier of traditional Chinese culture. The poem depicts the spring scenery in southern China during the Qingming Festival and the prosperity of social life.Įnabling more people to appreciate the charm of traditional Chinese culture The ancient Chinese poem on the painting is from Yong Liu, Northern Song Dynasty.
Image: The painting from “West Mountain in Misty Rain” by Shen Zhou, Ming Dynasty. Currently, literary Chinese translation has been integrated into the Microsoft Translator app, Azure Cognitive Services Translator, and a number of Microsoft products that are supported by Microsoft Translator services. To solve this problem, researchers at Microsoft Research Asia adopted the latest neural machine translation techniques to train direct translation models between literary Chinese and modern Chinese, which also results in creating translation capabilities between literary Chinese and more than 90 other languages and dialects in Microsoft Translator. However, similar to Shakespeare ’ s verses in the English language, the literary Chinese used by these poets is often difficult for modern day people to understand, and the meanings and subtleties embedded within it are frequently lost. This is a splendid cultural treasure that has been left behind for us. When reading ancient Chinese poetry, we often marvel at the very wonderful words ancient writers could use to describe people, events, objects, and scenes.
0 kommentar(er)
