A method of Part-Of-Speech guessing of Chinese Unknown Words based on combined features

Part-of-speech (POS) guessing of unknown words is an essential phase in the process of unknown words identification. This paper applies combined features (namely, both external and internal features) in POS guessing of Chinese unknown words, under conditional random field model (CRF). For acquiring high-precision of POS guessing, this paper puts forward a method of integrating Chinese radical, as a new internal feature of Chinese characters, into the existing feature set. Experiments show that the application of combined features is effective for POS guessing, and the new feature can significantly improve the performance of POS guessing (precision is up to 94.67%). The results also show that Chinese radical, as an effective internal feature in the field of lexical analysis, has a certain practical value.