A study on the generation of transformed Chinese sentences using generative AI
This study examined how 16 Chinese transformational structures are generated using generative AI from the perspective of learners whose native language is Korean. To summarize: (1) In weak AI models, using the zero-shot input method, Baidu generated 13 transformed Chinese Sentences, and Papago generated 11 transformed Chinese Sentences. (2) In strong AI models, using the prompt input method, WRTN generated 12 transformed Chinese Sentences, and Yuanbao generated 11 transformed Chinese Sentences. The possible reason why weak AI showed better results than strong AI may be because the analysis target was simple sentences. Baidu and Papago AI are programs specialized in translation. Therefore, under the same conditions as the experiment, it can posited that weak AI is more specialized than strong AI. Thus, it may be sufficient to utilize weak AI in current Chinese writing education. Nevertheless, for this research be applicable to Chinese writing education, the following additional analyses are necessary: (1) This study targeted ‘simple sentences.’ If applied to ‘complex sentence’ writing education, an analysis of whether weak AI remains useful is necessary. (2) An analysis of how to conduct education using Artificial Intelligence is required.
本研究從母語為韓語的學習者的視角出發,探討了生成式AI如何生成16種漢語變 形結構。總結如下:弱AI模型採用zero-shot輸入法時,Baidu生成了13個漢語 變形結構,Papago生成了11個漢語變形結構。強AI模型採用prompt輸入法時, WRTN生成了12個漢語變形結構,Yuanbao生成了11個漢語變形結構。弱AI表 現優於強AI的可能原因在於分析對象是簡單句。Baidu和Papago AI是專門從事 翻譯的程序。因此,在相同的實驗條件下,可以認爲弱AI比強AI更具專業性。由此 可見,在當前的漢語寫作教育中,利用弱AI可能就已足夠。然而,爲了將本研究 應用於漢語寫作教育,還需要進行以下額外分析:從研究對象拓展來講,本研究 針對的是“簡單句”。如果應用於“複雜句”寫作教育時,則需要分析弱AI是否仍然有 用。從AI輔助教學方法來講,還需要分析如何利用人工智能進行教學。