主要漢字形聲字發音規則探勘與視覺化

Primary Chinese Semantic-Phonetic Compounds Pronunciation Rules Mining and Visualization

近年華語教學的需求量與重要性日漸增加，為幫助漢語學習者構築現代漢字、增進學習效率，採用「部件教學法」，由部件當中找出漢字表音和表意的線索，故以形聲字與其聲符為研究對象。形聲字在現代漢語通用字中佔八成，大多是由一個表意的形符加上一個表音的聲符組成。本研究強調聲符表音的線索，以關聯式規則探勘出形聲字發音規則。並進一步地找出影響形聲字發音的關鍵因素，輔以漢語音韻學的知識，建立漢字發音的階層架構，進行多層次形聲字發音規則探勘，藉此幫助漢語學習者與教學研究歸納形聲字發音的脈絡。最後用視覺化的方式呈現這些規則，並設計簡單、好記的系統輔助漢字識字教學與漢字研究。

The demand and the importance of Chinese teaching have increased continuously. In order to assist the Chinese learners in composing Chinese characters and increase their learning efficiency, Chinese components teaching method is adopted. The learners can find the clues to both the pronunciations and the meanings of Chinese characters from Chinese components, and semantic-phonetic compounds and their phonetic components are exactly proper to be the object. There are 80.5% semantic-phonetic compounds in the 7000 common Chinese characters, and most of them are formed with one semantic component and one phonetic component. For the purpose of emphasizing the clues to the pronunciations of Chinese characters, multiple-level association rule mining was applied to discover the hierarchical pronunciation rules of semantic-phonetic compounds. This approach found the key factors which have the strong connection with the pronunciations of semantic-phonetic compounds. With the knowledge of Chinese linguistics, we constructed the hierarchical Chinese pronunciation structure. The hierarchical pronunciation rules are the overview of the pronunciations of semantic-phonetic compounds and aid both Chinese learning and Chinese researches. Therefore, they can learn the pronunciations of Chinese characters not only in the general aspect but the specific aspect. These rules were represented in visualization and the simple and memorable system was designed to assist both the Chinese literacy teaching and Chinese researches.