Learn Cantonese with Big Data

A Self-learning Open Platform of Chinese

This mobile app is a self-learning open platform of the Chinese language (including Cantonese). The platform draws on corpus linguistic technology and linguistic knowledge, such as usage frequencies of characters and words, word collocations, high frequency words, etc. The platform intends to provide Chinese language information and examples which are close to what are being used in daily life. This approach can help the users to learn and master the Chinese language in a more effective manner. Frontline teachers, dictionary compilers and learning materials designers can also benefit from this platform for curriculum design and teaching materials development.

Highlighted features of the platform:

- input of Chinese characters with photo-taking and OCR

- use of Chinese language corpus (big data)

- basic lexical information: parts-of-speech, stroke numbers, radical, display of the order of strokes

- usage information of words: usage frequency, verb-noun collocation, classifier-noun collocation

- other information: correspondence of vocabulary in South Asian languages (Urdu, Nepali, Hindi)