Detecting Word Misuse in Chinese
Wei Liu · 2010
Social Network Service (SNS) and personal blogs have become the most popular platform for online communication and sharing information. However because most modern computer keyboards are Latin-based, Asian language speakers (such as Chinese) has to rely on a input system which accepts Romanisation of the characters and convert them into characters or words in that language. In Chinese this form of Romanisation (usually called Pinyin) is highly ambiguous, word misuses often occur because the user choose a wrong candidate or deliverately substitute the word with another character string that has the identical Romanisation to convey certain semantics, or to achieve a sarcasm effect. In this paper we aim to develop a system that can automatically identify such word misuse, and suggest the correct word to be used. 1