Word Extraction Based on Mutual Information for Ancient Chinese Database

Word extraction is an important issue in archaic Chinese corpus processing. In this paper, we focus to extract multi-character word for an archaic Chinese database. The candidate words are extracted based on associative strength of characters. It is up to the user to judge whether a candidate word is real word or not. After a word is extracted, the mutual information that is related to it is modified accordingly. Word is extracted recursively. The empirical results show that mutual information method is an effective auxiliary approach to extract multi-character word for an archaic Chinese database