基于数据挖掘技术的汉语教学语料库建构

The Construction of Chinese Teaching Corpus Based on Data Mining Technology

随着语料库语言学的兴起和发展,基于语料库进行的第二语言教学受到第二语言教学界的高度重视。而在对外汉语教学界,并没有建立一个适应于汉语教学与学习需求的汉语教学语料库。特别是随着数据驱动学习模式的产生,加之语料大数据时代的到来,促使个性化、需求型的汉语教学与学习成为成大数据时代外语教学或第二语言教学的必然趋势。面对这一趋势,文章提出建构"汉语教学语料库"的基本设想。汉语教学语料库的建构以汉语本体语料库和汉语中介语语料库为基础,以数据挖掘技术和可视化技术为支撑。通过汉语教学语料库的建构,对于实现真正意义上的需求型、个性化学习具有重要的实践意义。

With the rise and development of corpus linguistics,the second language teaching based on corpus is highly valued by the second language teaching profession. However,in the field of teaching Chinese as a foreign language,there is not a corpus of Chinese teaching,which is adapted to the needs of Chinese teaching and learning. Especially,with the emergence of data-driven learning model and the arrival of big data age,the personalized,demand-based Chinese teaching and learning the inevitable trend of foreign language teaching or second language teaching of big data age. In the face of this trend,the article puts forward the basic idea that constructing 'Chinese teaching corpus'. The construction of Chinese teaching corpus is based on Chinese ontology corpus and Chinese Interlanguage corpus,and is supported by data mining technology and visualization technology. Through the construction of Chinese teaching corpus,it is of great practical significance to realize the demand type and individualized learning in the real sense.