Disambiguating Effectively Chinese Polyphonic Ambiguity Based on Unify Approach

摘要

One of the difficult tasks on Natural Language Processing (NLP) is to resolve the sense ambiguity of characters or words on text, such as polyphones, homonymy, and homograph. The paper addresses the ambiguity issue of Chinese character polyphones and disambiguity approaches for such issues. Three methods, dictionary matching, language models and voting scheme, are used to disambiguate the prediction of polyphones. The best precision rate for these methods achieves 92.65%. Furthermore we proposed the unify approaches to improve the performance with respect to various threshold value. Comparing with the well-known MS Word 2007, our approach is superior and enhances the final precision rate up to 93.32%.